<a href="https://www.adacore.com/gnatpro/assurance" target="_blank" rel="noreferrer noopener">GNAT Pro Assurance</a> customers have access to a special variant of GNATcheck called GNATkp (GNAT Known Problems detector). This tool is packaged with rules designed to detect Ada constructs affected by known problems in compiler releases. Note that GNATkp is an addition to and not a replacement for GNATcheck.Replacing error-prone manual code inspection with an automatic and systematic verification relevant to specific GNAT Pro versions and targets, GNATkp ensures that your code remains robust and free from potential bugs introduced by known problems. It integrates seamlessly into existing workflows, offering a targeted approach to safeguarding software quality,Let’s consider one example.Here is the definition of a data structure that triggers an invalid code generation on GNAT 17 for powerpc targets only:<pre><code>A record component whose type is a record type with an Unchecked_Union and a representation clause specifying a size that is not a power of two for some of the fields.</code></pre>As you can see, the triggering condition is very precise, and not easy to spot during code review, while weakening it is liable to introduce many false positives.Here is a piece of code that matches:<pre><code>type A (Kind : Boolean := True) is record
 case Kind is
 when True =&gt;
 A1 : Integer;
 when False =&gt;
 A2 : Boolean;
 end case;
 end record
 with Unchecked_Union;
    
 for A use record
 A1 at 0 range 0 .. 31;
 A2 at 0 range 0 .. 12; -- Note the size is not a power of 2
 end record;

 type B is record
 AF : A;
 end record;</code></pre>Now let’s see how we can use GNATkp to spot the problem.There are two important switches for GNATkp:<ul><li dir="ltr">--kp-version: Specify the compiler version used</li><li dir="ltr">--target: Specify the target architecture</li></ul><pre><code>$ gnatkp --kp-version=17.1 --target=powerpc -P simple.gpr
info: kp_s124_035 enabled
info: kp_s814_034 enabled
info: kp_u727_033 disabled, target does not match
info: kp_v120_015 enabled
main.adb:19:08: possible occurrence of KP V120-015 on powerpc targets</code></pre>GNATkp lists all the known problems for the given GNAT version. Problems specific to a target architecture are either disabled or enabled depending on the --target switch. Then, for each enabled problem, a rule is checked against the project source code.Infringing pieces of code will result in a message like this one:<pre><code>main.adb:19:08: possible occurrence of KP V120-015 on powerpc targets</code></pre>Under the hood, GNATkp rules, like GNATcheck rules, are written using the&nbsp;<a href="https://docs.adacore.com/live/wave/lkql/html/gnatcheck_rm/gnatcheck_rm/lkql_language_reference.html">LKQL</a> (short for LangKit Query Language). This means you can implement your own rules to detect other forbidden constructs, e.g. related to hardware malfunctions.GNATkp can be integrated into developers’ workflows, continuous integration systems, or certification processes. In summary, it empowers teams to proactively manage known compiler-related issues. By integrating GNATkp into your development process, you can significantly reduce the chances of encountering costly or hazardous errors in deployed systems.

GNAT Pro Assurance customers have access to a special variant of GNATcheck called GNATkp (GNAT Known Problems detector). This tool is packaged with rules designed to detect Ada constructs affected by known problems in compiler releases.

How GNATkp Safeguards Against Known Compiler Issues

Researchers in the <a href="https://seas.harvard.edu/">Harvard John A. Paulson School of Engineering and Applied Sciences</a> (SEAS) have developed a machine learning framework that can predict with quantum-level accuracy how materials respond to electric fields, up to the scale of a million atoms – vastly accelerating simulations beyond quantum mechanical methods, which can model only a few hundred atoms at a time.The work will allow scientists and engineers to carry out highly accurate, large-scale simulations of different materials’ responses to many external stimuli, which could have major implications for advanced materials design or energy technologies.The research was published in <a href="https://www.nature.com/articles/s41467-025-59304-1" target="_blank">Nature Communications</a> and led by Stefano Falletta, a former postdoctoral researcher in the group of senior author <a href="https://seas.harvard.edu/person/boris-kozinsky">Boris Kozinsky</a>, the Gordon McKay Professor of Materials Science and Mechanical Engineering at SEAS, and Professor of Chemistry and Chemical Biology.For more than 30 years, the primary method for simulating the properties and behaviors of atoms and molecules has been density functional theory, a set of quantum-mechanical equations that is physics-based and highly accurate, but computationally intensive and thus limited to only smaller systems.In recent years, studying quantum behavior of materials at larger sizes and longer time scales while retaining the accuracy of density functional theory has been bolstered by machine learning, but modeling responses to external stimuli has remained a challenge. This is because existing machine learning methods tend to overlook physical symmetries and conservation laws related to both energetic and electrical properties, leading to inaccuracies in property predictions.To solve these issues, the authors devised a machine learning method that unifies distinct quantum behaviors like energy and polarization into one generalized potential energy function. Using density functional theory calculations as training and validation data, the model includes the effects of external fields and enforces the correct physics. &nbsp;The new framework, called Allegro-pol, builds on a previously developed neural network architecture called <a href="https://www.nature.com/articles/s41467-023-36329-y" target="_blank">Allegro</a> that performed accurate simulations of the energy and atomic forces present in a given set of atoms. Falletta looked to extend the capabilities of Allegro to capture not only real-time molecular dynamics, but also, what happens when the atoms undergo external perturbations, such as the application of an external electric field. Understanding these interactions is essential for discovering, for example, new ferroelectric materials and dielectric materials that could be used in applications such as non-volatile memory, capacitors, and energy storage devices.“If you use physics-based methods that solve quantum mechanical equations, you can only go up to a few hundred atoms,” said Falletta. “Whereas with these machine learning methods, you can essentially scale up to hundreds of thousands of atoms or even a million.”They proved out their method by simulating infrared and electrical properties of silicon dioxide, as well as temperature-dependent ferroelectric switching in barium titanate.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1750809014857-ezgif-840a3fb3791f38.gif" style="width: 100%px;" class="fr-fic fr-dib">Separations of electric poles in tetragonal barium titanate during transition from up to down polarization in the presence of an electric field.Falletta, who now works at&nbsp;<a href="https://www.radical-ai.com/" target="_blank">Radical AI</a> on accelerating materials discovery, said that foundational models based on the one described in Nature Communications could allow machine learning-enabled materials science to take off in ways only beginning to be understood. &nbsp;&nbsp;“The field of computational materials discovery is moving toward better theories, better machine learning models, better infrastructure, bigger clusters, faster GPUs, and better generative models – it’s all kind of coming together,” Falletta said. “It’s definitely very exciting.”<hr>The paper was co-authored by Andrea Cepellotti, Anders Johansson, Chuin Wei Tan, Marc L. Descoteaux, Albert Musaelian, and Cameron J. Owen. The research was supported primarily by the National Science Foundation through the Harvard University Materials Research Science and Engineering Center Grant No. DMR-2011754; the U.S. Department of Energy, Office of Basic Energy Sciences Award No. ML-22-075; and the Department of Navy award N00014-20-1-2418 issued by the Office of Naval Research and Robert Bosch LLC.

Machine-learning framework predicts effects of electric fields

Modeling electric response of materials, a million atoms at a time

Preterm birth complications are the primary cause of death among children under age 5, and nearly 75% could be prevented with interventions, according to the World Health Organization. While the causes leading to preterm birth are largely unknown, an interdisciplinary research team at Washington University in St. Louis has found that variability in sleep patterns in people experiencing pregnancy can effectively predict preterm birth.<a href="https://benwarner.net/">Ben Warner</a>, a doctoral student in the McKelvey School of Engineering, and&nbsp;<a href="https://obgyn.wustl.edu/people/peinan-zhao-phd/">Peinan Zhao</a>, assistant professor of obstetrics &amp; gynecology at WashU Medicine, used machine learning models to analyze sleep data from participants experiencing pregnancy. While disrupted sleep is known as a predictor of preterm birth, which is delivery before 37 weeks’ gestation, the reasons behind it have been unclear because the data was self-reported by patients.Warner, who is advised by&nbsp;<a href="https://engineering.washu.edu/faculty/Chenyang-Lu.html">Chenyang Lu</a>, the Fullgraf Professor in the Department of Computer Science &amp; Engineering in McKelvey Engineering; Zhao; and&nbsp;<a href="https://reproductivesciences.wustl.edu/people/sarah-england-phd/">Sarah England</a>, the Alan A. and Edith L. Wolff Professor and vice chair for research of obstetrics and gynecology at WashU Medicine, studied data from 665 patients in the first two trimesters of their pregnancy with a recorded delivery date. The patients were in a 2014 cohort study conducted at Washington University in St. Louis and BJC HealthCare. About 14% of patients in the cohort experienced a preterm birth.The patients wore a clinically validated wristwatch, called an actigraph, that measured body movements for roughly two-week periods. The data allows the team to extract daily patterns in the length of sleep, what time the patients went to sleep and woke up, their movement during sleep and several other variables. Patients also completed surveys about their sleep patterns. Warner and Zhao combined the two sources of data and plugged them into machine learning models to learn the impact of sleep patterns on preterm birth.“We found that measures of sleep are decently predictive of preterm birth,” Warner said. “Variability in sleep patterns tends to be a stronger predictor of preterm birth than average sleep metrics, and getting consistent sleep is more important than getting good sleep on average.”Lu’s lab has studied data from wearable devices for a wide variety of issues including contact tracing for COVID-19, predicting surgical outcomes and detecting depression and anxiety.“Raw data from wearables can be very messy, but using a healthy combination of statistical methods, AI and clinical knowledge, researchers can extract important clinical insights,” said Lu, also director of the university’s AI for Health Institute. “Then AI scientists and clinicians work together to extract the insights from these very complex data from the real world and get meaningful insights from it.”Zhao said their models were intentionally simple and looked for clinically significant association within the results.“Our model shows that a machine learning model is better than a more statistical model,” said Zhao, who also is a member of the Center for Reproductive Health Sciences. “We can look at the result on importance of individual variables: How much does this variable contribute to the predictive model, and how much does it affect the final result? Based on that, a direction of a potential intervention is to promote a more consistent sleep schedule.”Although many people experiencing pregnancy report disrupted sleep, that generally comes in the third trimester, England said. The team focused on finding signals before women were 20 weeks pregnant.“There is no intervention because we can’t predict who’s going to have a preterm birth,” said England, director of the Center for Reproductive Health Sciences. “We’re hoping that this will be much more helpful in getting predictive power of women who are going to be at higher risk.”Looking ahead, the team plans to validate the results in other populations at other academic medical centers.“This research highlights the collaborations between engineering and obstetrics and gynecology,” England said. “Many people don't see natural connections between engineering and the field of reproduction, and this is another example of a perfect way for engineers to interact with researchers in our field.”<hr>Warner BC, Zhao P, Herzog ED, Frolova AI, England SK, Lu C. Validation of sleep-based actigraphy machine learning models for prediction of preterm birth. npj Women’s Health. June 20, 2025. DOI:&nbsp;<a href="https://www.nature.com/articles/s44294-025-00082-y">10.1038/s44294-025-00082-y</a>.

An interdisciplinary research team at Washington University in St. Louis has found that variability in sleep patterns in people experiencing pregnancy can effectively predict preterm birth. (Credit: Unsplash)

WashU interdisciplinary research uses machine learning to offer accurate prediction of preterm birth

Sleep data from wearable device may help predict preterm birth

Anyone who has seen a fluid mechanics simulation in action, relied on a weather model to anticipate an oncoming hurricane, or seen a flight simulator put a virtual, billion-dollar jet design through the paces knows that the mathematics of simulation are almost-impossibly complex. Even on the fastest supercomputers, these calculations can sometimes take days to complete.Now, researchers at Stanford University have discovered a way to not only expedite modeling calculations but actually produce better results by gathering fewer-but-higher-quality data and removing redundancies that bog down traditional approaches. They achieved this by using a new approach that simplifies the data inputs to speed calculations.“The key takeaway from this work is that, by being smart about what data we collect, we can significantly reduce the amount of data required to construct accurate models of complex systems,” said <a href="https://profiles.stanford.edu/joshua-ott">Joshua Ott</a>, a doctoral student in aeronautics and astronautics engineering and first author of the new paper appearing at the Learning for Dynamics &amp; Control Conference (L4DC). “If you can simplify the data inputs, you make the math easier.”<h2>Simplify to expedite</h2>The vision, explains co-author <a href="https://profiles.stanford.edu/mykel-kochenderfer">Mykel Kochenderfer</a>, professor of aeronautics and astronautics, is to reduce the scale of the calculations to only the most important, enabling elimination of redundant data and acceleration of calculation times.“Our work involves new methods for efficiently learning the behavior of complex systems—like aircraft, weather, or financial markets—by collecting smart, targeted data,” Kochenderfer said. “Understanding these systems accurately is important in science and engineering, but gathering the necessary data can be time-consuming and expensive.”In lay terms, the team's approach to the problem was to force it through a series of smaller, easier-to-solve approximations, allowing them to solve the problems extremely quickly.“Technically, that type of modeling is not as accurate as if you did the full, optimization, but we solve it many more times and over time we narrow in on better answers, faster,” Ott explained.<h2>Valid proof</h2>The team experimentally validated its method in three unrelated simulation environments using two conventional techniques. “Just to give you an idea of the scale of these problems: An aircraft simulation typically has perhaps 20 dimensions to calculate, but a fluid flow simulation may have 50,000 or more.”In one experiment they did calculations of fluids flowing past a rotating cylinder — the sort of problem that has 50,000-plus inputs. In another they simulated the flight of an F-16 fighter jet, reducing the inputs to just four controls—throttle percentage, elevator, aileron, and rudder deflections.“It's quite a difference in scale, but the method still works at both scales,” Ott said. “That's pretty cool.”Last, to demonstrate the usefulness of their method in real-world situations, the team integrated its method into X-Plane, a highly realistic flight simulator for pilot training and research purposes. X-Plane required real-time updates and adjustments to control inputs based on the current state of the aircraft. They then used a simulated X-Plane to demonstrate the real-time use-case of their method.“This last example, in particular, showcases the practical applicability of our method in scenarios that require adaptive and responsive control strategies and the speed of our method to update estimates and replan onboard a running aircraft,” said <a href="https://profiles.stanford.edu/stephen-boyd">Stephen Boyd</a>, professor of electrical engineering, an expert in control systems and senior author of the paper.<h2>In the real world</h2>The researchers note that this approach might significantly lessen time to certify new aircraft designs to ensure that aircraft are safe and meet performance standards, potentially lowering costs for both airlines and passengers. It might also be applied to climate systems to improve climate projections and identifying areas where current models tend to be most uncertain to refine our understanding of climate patterns, improve predictions, and better inform policy decisions. In that regard, next up for the team, Ott said, is a research collaboration with the Air Force Test Pilot School looking at applying it to their T-38 jets.“The T-38 is quite a bit faster than a Cessna 172. Demonstrating our method onboard the T-38 in real time could open doors for future avenues to accelerate the flight test and certification process across the board. “We're trying to work in a way that we can get the best of both worlds — the accuracy of the traditional methods and the speed of our pared-down approach. It should be a fun challenge.”

Image of the Cessna 172 aircraft used for the experiments in the X-Plane simulator with illustrations showing possible future trajectories of the system with uncertainty bounds. | Image courtesy of Joshua Ott using X-Plane by Laminar Research.

Researchers show how collecting fewer, higher-quality data points can speed simulation algorithms and produce better results.

Less is more: How less data can lead to better models

The application is very simple: wear the sanitary towel with the integrated non-electronic sensor, take a picture of the used towel with your smartphone and use the app to analyse it. MenstruAI is designed to enable users to check their health regularly and effortlessly. For the first time ever, a new technology from ETH Zurich is bringing a tracking tool to a place where hardly anyone would expect it: the sanitary towel.<h2>Menstrual blood is a source of information</h2>Over 1.8 billion individuals menstruate, yet menstrual blood hardly plays any role in medicine. “This reflects a systemic lack of interest in women’s health,” states Lucas Dosnon, first author and doctoral student in the group of Inge Herrmann, a professor at the University of Zurich, Balgrist University Hospital, Empa and accredited at the Department of Mechanical and Process Engineering at ETH Zurich.“To date, menstrual blood has been regarded as waste. We are showing that it is a valuable source of information,” says Dosnon. Menstrual blood contains hundreds of proteins, and for many of them there is a correlation with their concentration in venous blood. Numerous diseases, including tumours such as ovarian cancer or endometriosis, lead to the presence of certain proteins in blood, which can serve as biomarkers for disease detection.The ETH researchers used three biomarkers as a starting point for MenstruAI. They currently record the C-reactive protein (CRP) as a general inflammation marker, the tumour marker CEA typically elevated in all kinds of cancers and CA-125, a protein that can be elevated in endometriosis as well as in ovarian cancer. Many more protein-based biomarkers are being currently investigated and will be added to the list to reflect many other aspects of an individual’s health.<h2>The same functionality as a Covid test</h2>MenstruAI makes use of a paper-based rapid test strip, a principle that is also familiar from Covid self-tests – however, this time analysing blood instead of saliva. When the biomarker in the menstrual blood comes into contact with a specific antibody on the test strip, a coloured indicator appears. This varies in colour intensity depending on the concentration of the corresponding protein. The higher the concentration, the darker the colour will be. The test area is embedded in a novel small flexible silicone chamber, which can be combined with a commercially available sanitary towel. Thanks to its innovative nature, only a controlled volume of blood reaches the sensor – without smearing or falsifying the test.The results can be read with the naked eye or with a specially developed app based on machine learning that evaluates the colour intensity. “The app also recognises subtle differences, such as the amount of proteins present, and makes the result objectively measurable,” explains Dosnon.<h2>Does it actually work in everyday life?</h2>Following an initial feasibility study with volunteers, the researchers are now planning a larger field study involving over one hundred people. The aim is to test the suitability of MenstruAI for everyday use under real-life conditions and to compare the values measured with established laboratory methods.Another focus is on the biological diversity of menstrual blood: the composition varies depending on the day of the cycle as well as between individuals. This heterogeneity must be recorded and analysed – a pivotal step for clinical validation. Moreover, regulatory requirements must also be checked with a view to possible market authorisation, for example, biocompatibility must be assessed. The materials involved, however, are considered safe.At the same time, the team is working with design experts from the Zurich University of the Arts (ZHdK). The aim is to further optimise the user experience, thereby keeping the psychological barrier as low as possible. “It’s also about designing the technology in such a way that makes it technically and socially acceptable,” says Herrmann.<h2>Inexpensive, but no substitute for medical advice</h2>The technology integrated within the pad works without laboratory equipment. “Right from the outset, the aim was to develop a solution that can also be used in regions with poor healthcare provision and would be as cost-effective as possible, potentially enabling population-based screening,” says Herrmann.Consequently, MenstruAI can serve as an early warning system – users can seek medical advice in the event of abnormal values. It is not intended to replace established diagnostics, but to provide information on when a visit to the doctor's might be expedient. In addition, health progression can be monitored over the long term and any changes can be better understood.Herrmann and Dosnon regard MenstruAI as more than just a technical project. It is a contribution to more equitable healthcare. “When we talk about healthcare, we can’t simply phase out half of humanity,” Herrmann underlines. The researchers were amazed at the extent to which the topic of menstruation is still stigmatized, including in academic circles, and that many declared their idea to be nauseous or impractical. Dosnon is convinced, however: “Courageous projects are called for to break down existing patterns of behaviour to ensure that women’s health finally takes the place it deserves.”<a></a><a></a><hr /><h2>References</h2>Dosnon L, Rduch T, Meyer Ch, Herrmann IK: A wearable in-pad diagnostic for the detection of disease biomarkers in menstrual blood, Advanced Science (2025), DOI: <a href="https://advanced.onlinelibrary.wiley.com/doi/10.1002/advs.202505170?af=R">external page10.1002/advs.202505170</a>

Colour changes on the sanitary towel can be interpreted by eye or photographed with a smartphone and evaluated directly in the app. The prototype has a dot with a control dot on the test strip for each biomarker. (Image, AI generated: Lucas Dosnon and Josef Kuster / ETH Zurich)

Researchers at ETH Zurich have developed the first technology that is able to recognise biomarkers in menstrual blood – directly in sanitary towels. MenstruAI promises a simple, non-invasive method for recording health data in everyday life.

Sanitary towels morph into test strips

What exactly is “trustworthy artificial intelligence”? For now, there’s no clear, universally accepted definition, although the European Union’s AI Act goes one step in this direction with its seven principles of trustworthy AI: human agency and oversight; technical robustness and safety; privacy and data governance; transparency; diversity, non-discrimination and fairness; societal and environmental well-being; and accountability.Applying these principles is much easier said than done, however, especially when biases come into play – whether ideological, political, religious, race- or gender-based, or more generally cognitive. “Biases are nothing new – as humans, we’re full of them,” says Olivier Crochat, the head of <a href="https://c4dt.epfl.ch/">EPFL’s Center for Digital Trust (</a>C4DT). “Generative AI should enable to bring this issue up, both for people who develop the programs and those who use them.”“Biased output from a model could end up being used to train other models, thus compounding the bias,” he says. In other words, algorithms trained on biased data will merely reproduce the distortion. And because these algorithms are increasingly used for such things as making hiring decisions, reviewing mortgage applications and performing facial recognition, they could have a direct impact on peoples’ lives. The EU AI Act specifies that, to be truly trustworthy, a GenAI program must not only be transparent and secure, but also designed to detect and correct biases.One concern is that algorithms trained on fake news, conspiracy theories, biases, propaganda and censored information will simply amplify that noise and become weapons of mass disinformation. “In theory, algorithms won’t make content any worse than it already is,” says Crochat, “however, if we don’t rectify this issue, it will carry on, and once amplified at large scale, it could have disastrous consequences.” In this regard, a recent report from the <a href="https://www.media-initiative.ch/" target="_blank" rel="noopener">EPFL-based Initiative for Media Innovation </a>(IMI) is encouraging. The IMI study examined various elections held in 2024 – a year when nearly half of the world’s citizens went to the polls. It found that AI-driven programs had only a marginal impact and didn’t swing the elections one way or the other. However, the study did find that the spread of manipulated content, boosted by algorithms, divided political opinion further and created a widespread climate of mistrust.In theory, algorithms won’t make content any worse than it already is, however, if we don’t rectify this issue, it will carry on, and once amplified at large scale, it could have disastrous consequences.Olivier Crochat, head of EPFL’s Center for Digital Trust (C4DT)<h2>Shared responsibility</h2>The authors stress that the use of digitally manipulated content for propaganda purposes is nothing new – GenAI has only magnified this practice. “It’s a game of cat and mouse between the creators of AI technology to generate deepfakes and the developers of software to detect them,” says Prof. Touradj Ebrahimi, an EPFL expert in multimedia signal processing. His research group is working to develop systems for identifying and limiting the spread of manipulated content. C4DT director adds: “It still boils down to computer programming – if we know exactly what the problem is, we can find ways to solve it. And the upshot is that if we correct a bias in an AI model, it’ll instantly disappear for millions of users.”However, that doesn’t make the issue of trustworthy AI any less important. Most GenAI programs are developed and hosted by profit-seeking businesses that shift some of the responsibility to users. This raises ethical and legal questions about the role that social values should play in AI governance.“While ultimately the use of AI is the responsibility of users, regulatory mechanisms can – and should – be implemented to curb the risk of premeditated or accidental malicious use, much like the safety lock on guns or the safety cap on medicine bottles,” says Sabine Süsstrunk, head of EPFL’s Visual Representation Lab and president of the Swiss Science Council. “Proven strategies such as certification, regulation and education are needed to guarantee minimal acceptable performance, clarify responsibility and heighten public awareness.”Johan Rochel, an EPFL lecturer on the ethics and law of AI and co-head of the Lab for Innovation Ethics (ethix), explains that responsibility isn’t a binary concept – it’s something that should be distributed along the entire value chain. Every decision that programmers make as they develop an AI system involves ethical choices and trade-offs that should be assessed well before their consequences become visible.<h2>More isn’t always better</h2>Another important issue relates to the huge datasets that are used to train GenAI algorithms. Many of these datasets come from businesses, with little transparency on where the data came from. Large tech companies often set aside ethical considerations when asked about intellectual property or how representative their datasets are, arguing that the more data they can feed into their algorithms, the better their AI programs will perform.“But more isn’t always better – what matters is having quality data,” says Rochel. “Volume shouldn’t take priority over ethics.” Süsstrunk agrees: “If the data is copyrighted, it must either be licensed, purchased or not used at all. Unfortunately, given the inconsistent enforcement of copyright laws across jurisdictions, the current situation is far from satisfactory.”<hr /><h3>Using GENERATIVE AI responsibly and transparently</h3>Like many universities, businesses and other organizations, EPFL has issued guidelines on the use of generative artificial intelligence (GenAI). This technology has huge potential, but we want to make sure it’s used in an informed, transparent and responsible way. Using GenAI in an informed way means making users aware of its limitations and risks and of the importance of not feeding personal or confidential data into these programs. Using GenAI responsibly means encouraging users to check whether the content produced by these programs is correct, objective, reliable and compliant with copyright law. Users will bear final responsibility for the content. Being responsible also includes bearing in mind the energy consumption of GenAI systems. Using this technology transparently means clearly indicating that the content was produced by GenAI. <a href="https://www.epfl.ch/about/vice-presidencies/vice-presidency-for-academic-affairs-vpa/tips-for-the-use-of-generative-ai-in-research-and-education/">EPFL’s guidelines, which are intended for everyone in the School community, are available on our website and updated regularly.</a>

Generative artificial intelligence (GenAI) suffers from several types of biases that reflect human failings. How can we avoid being tricked?

Staking out a path to trustworthy AI

Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a novel artificial intelligence model inspired by neural oscillations in the brain, with the goal of significantly advancing how machine learning algorithms handle long sequences of data.AI often struggles with analyzing complex information that unfolds over long periods of time, such as climate trends, biological signals, or financial data. One new type of AI model, called "state-space models," has been designed specifically to understand these sequential patterns more effectively. However, existing state-space models often face challenges — they can become unstable or require a significant amount of computational resources when processing long data sequences.To address these issues, CSAIL researchers T. Konstantin Rusch and Daniela Rus have developed what they call “linear oscillatory state-space models” (LinOSS), which leverage principles of forced harmonic oscillators — a concept deeply rooted in physics and observed in biological neural networks. This approach provides stable, expressive, and computationally efficient predictions without overly restrictive conditions on the model parameters."Our goal was to capture the stability and efficiency seen in biological neural systems and translate these principles into a machine learning framework," explains Rusch. "With LinOSS, we can now reliably learn long-range interactions, even in sequences spanning hundreds of thousands of data points or more."The LinOSS model is unique in ensuring stable prediction by requiring far less restrictive design choices than previous methods. Moreover, the researchers rigorously proved the model’s universal approximation capability, meaning it can approximate any continuous, causal function relating input and output sequences.Empirical testing demonstrated that LinOSS consistently outperformed existing state-of-the-art models across various demanding sequence classification and forecasting tasks. Notably, LinOSS outperformed the widely-used Mamba model by nearly two times in tasks involving sequences of extreme length.Recognized for its significance, the research was selected for an oral presentation at ICLR 2025 — an honor awarded to only the top 1 percent of submissions. The MIT researchers anticipate that the LinOSS model could significantly impact any fields that would benefit from accurate and efficient long-horizon forecasting and classification, including health-care analytics, climate science, autonomous driving, and financial forecasting."This work exemplifies how mathematical rigor can lead to performance breakthroughs and broad applications," Rus says. "With LinOSS, we’re providing the scientific community with a powerful tool for understanding and predicting complex systems, bridging the gap between biological inspiration and computational innovation."The team imagines that the emergence of a new paradigm like LinOSS will be of interest to machine learning practitioners to build upon. Looking ahead, the researchers plan to apply their model to an even wider range of different data modalities. Moreover, they suggest that LinOSS could provide valuable insights into neuroscience, potentially deepening our understanding of the brain itself. Their work was supported by the Swiss National Science Foundation, the Schmidt AI2050 program, and the U.S. Department of the Air Force Artificial Intelligence Accelerator.

“Linear oscillatory state-space models” leverage principles of forced harmonic oscillators — a concept deeply rooted in physics and observed in biological neural networks. This can improve how we predict complex information like climate trends or financial data. Image: Pixabay

New type of "state-space model" leverages principles of harmonic oscillators.

Novel AI model inspired by neural dynamics from the brain

﻿This article is based on a conversation with Fabio Rosa, CEO of Tago.io.Pilots are not to prove the technology, it's to prove your business caseIn today’s IoT landscape, the technology has proven itself. Sensors are accurate. Devices are reliable. Connectivity is everywhere; from 4G and 5G to LoRaWAN and non-terrestrial networks. And IoT platforms are powerful, flexible, and customizable.Yet, despite this maturity, too many IoT projects don't make it past the pilot phase.Why?Because companies often treat pilots as technical exercises, instead of what they truly are: business case validations.<h2>5 questions to ask yourself during the pilot phase</h2>A real pilot should force you, and your team, to face some hard truths. Here are five critical questions to ask yourself:<ol><li>What is the minimum required scale for this project to succeed? Companies often over-estimate the scale and speed of hardware rollouts. Take an honest look at the numbers and define the required scale of the project to make the numbers work. </li><li>If I would get free access to hardware / connectivity / IoT platforms, would the business case look significantly different? There’s an obsession with costs, leading to tough negotiations to scrape off cents per device. If these negotiations have a significant impact on the business case of your IoT project, something is awfully off.  </li><li>Am I ready to change the roles and responsibilities of my personnel if the pilot succeeds?  IoT solutions streamline operations and automate tasks previously handled manually. If your project delivers the expected efficiencies, it will impact job roles and performance metrics. Are you ready to adjust how you evaluate, reward, and organize your team? Are you truly ready for the consequences of success? </li><li>What transformation does my company need to go through when implementing this IoT project? New processes, new skills, new departments. A real pilot highlights the organizational changes you must be willing to make, and the likelihood of these changes to succeed. The metrics used to define the success of projects and performance need to be realigned. </li><li>What additional resources do I need for installing and maintaining the solution?  Every connected device requires maintenance, support, and updates. Factor those into your business case at this phase, not during the production phase. Leaders and managers should be prepared to run a marathon, not a sprint. Therefore, additional resources and budget are necessary to achieve the long-term goals.</li></ol><h2>Focus where it matters</h2>A successful pilot is not one where everything "works" from a technical perspective. A successful pilot is one that proves your business case, that shows you can scale economically, create real value, and transform your operations sustainably.When you start treating pilots this way, your entire IoT strategy will change for the better. If you want a partner who understands this mindset, and who can help you build IoT projects that go beyond the pilot phase, talk to the team of <a href="https://tago.io/" target="_blank">TagoIO</a>.  <h2>About TagoIO</h2>TagoIO is an industry-leading IoT platform designed to empower businesses and individuals to connect, manage, and analyze the growing amounts of data IoT devices generate. The all-in-one platform streamlines data processing and visualization by eliminating complexity, saving businesses time, and freeing up resources so they can innovate their products and services.The platform is trusted by thousands of businesses that customize and deploy as the backbone of their solutions to connect IoT devices to hundreds of thousands of users worldwide. TagoIO has become a go-to solution for many IoT applications across many verticals, such as Agriculture, Buildings, Energy, Industrial, and Logistics.From its headquarters in Raleigh, NC, USA, TagoIO supports domestic and international businesses in more than 130 countries to build the best IoT solution. For more information, visit <a href="http://www.tago.io" target="_blank">www.tago.io</a>

IoT projects do not fail because of the technology, they fail because of bad business cases.

5 questions to ask yourself during the pilot phase

If there’s one thing that characterizes driving in any major city, it’s the constant stop-and-go as traffic lights change and as cars and trucks merge and separate and turn and park. This constant stopping and starting is extremely inefficient, driving up the amount of pollution, including greenhouse gases, that gets emitted per mile of driving. One approach to counter this is known as eco-driving, which can be installed as a control system in autonomous vehicles to improve their efficiency.How much of a difference could that make? Would the impact of such systems in reducing emissions be worth the investment in the technology? Addressing such questions is one of a broad category of optimization problems that have been difficult for researchers to address, and it has been difficult to test the solutions they come up with. These are problems that involve many different agents, such as the many different kinds of vehicles in a city, and different factors that influence their emissions, including speed, weather, road conditions, and traffic light timing.“We got interested a few years ago in the question: Is there something that automated vehicles could do here in terms of mitigating emissions?” says Cathy Wu, the Thomas D. and Virginia W. Cabot Career Development Associate Professor in the Department of Civil and Environmental Engineering and the Institute for Data, Systems, and Society (IDSS) at MIT, and a principal investigator in the Laboratory for Information and Decision Systems. “Is it a drop in the bucket, or is it something to think about?,” she wondered.To address such a question involving so many components, the first requirement is to gather all available data about the system, from many sources. One is the layout of the network’s topology, Wu says, in this case a map of all the intersections in each city. Then there are U.S. Geological Survey data showing the elevations, to determine the grade of the roads. There are also data on temperature and humidity, data on the mix of vehicle types and ages, and on the mix of fuel types.Eco-driving involves making small adjustments to minimize unnecessary fuel consumption. For example, as cars approach a traffic light that has turned red, “there’s no point in me driving as fast as possible to the red light,” she says. By just coasting, “I am not burning gas or electricity in the meantime.” If one car, such as an automated vehicle, slows down at the approach to an intersection, then the conventional, non-automated cars behind it will also be forced to slow down, so the impact of such efficient driving can extend far beyond just the car that is doing it.That’s the basic idea behind eco-driving, Wu says. But to figure out the impact of such measures, “these are challenging optimization problems” involving many different factors and parameters, “so there is a wave of interest right now in how to solve hard control problems using AI.” The new benchmark system that Wu and her collaborators developed based on urban eco-driving, which they call “IntersectionZoo,” is intended to help address part of that need. The benchmark was described in detail in a <a href="https://openreview.net/pdf?id=XoulHHQGFi">paper</a> presented at the 2025 International Conference on Learning Representation in Singapore.Looking at approaches that have been used to address such complex problems, Wu says an important category of methods is multi-agent deep reinforcement learning (DRL), but a lack of adequate standard benchmarks to evaluate the results of such methods has hampered progress in the field.The new benchmark is intended to address an important issue that Wu and her team identified two years ago, which is that with most existing deep reinforcement learning algorithms, when trained for one specific situation (e.g., one particular intersection), the result does not remain relevant when even small modifications are made, such as adding a bike lane or changing the timing of a traffic light, even when they are allowed to train for the modified scenario.In fact, Wu points out, this problem of non-generalizability “is not unique to traffic,” she says. “It goes back down all the way to canonical tasks that the community uses to evaluate progress in algorithm design.” But because most such canonical tasks do not involve making modifications, “it’s hard to know if your algorithm is making progress on this kind of robustness issue, if we don’t evaluate for that.”While there are many benchmarks that are currently used to evaluate algorithmic progress in DRL, she says, “this eco-driving problem features a rich set of characteristics that are important in solving real-world problems, especially from the generalizability point of view, and that no other benchmark satisfies.” This is why the 1 million data-driven traffic scenarios in IntersectionZoo uniquely position it to advance the progress in DRL generalizability.  As a result, “this benchmark adds to the richness of ways to evaluate deep RL algorithms and progress.”And as for the initial question about city traffic, one focus of ongoing work will be applying this newly developed benchmarking tool to address the particular case of how much impact on emissions would come from implementing eco-driving in automated vehicles in a city, depending on what percentage of such vehicles are actually deployed.But Wu adds that “rather than making something that can deploy eco-driving at a city scale, the main goal of this study is to support the development of general-purpose deep reinforcement learning algorithms, that can be applied to this application, but also to all these other applications — autonomous driving, video games, security problems, robotics problems, warehousing, classical control problems.”Wu adds that “the project’s goal is to provide this as a tool for researchers, that’s openly available.” IntersectionZoo, and the documentation on how to use it, are freely available at <a href="https://github.com/mit-wu-lab/IntersectionZoo">GitHub</a>.Wu is joined on the paper by lead authors Vindula Jayawardana, a graduate student in MIT’s Department of Electrical Engineering and Computer Science (EECS); Baptiste Freydt, a graduate student from ETH Zurich; and co-authors Ao Qu, a graduate student in transportation; Cameron Hickert, an IDSS graduate student; and Zhongxia Yan PhD ’24.

“We got interested a few years ago in the question, is there something that automated vehicles could do here in terms of mitigating emissions,” says MIT Professor Cathy Wu. “Is it a drop in the bucket, or is it something to think about?” Image: iStock

"IntersectionZoo," a benchmarking tool, uses a real-world traffic problem to test progress in deep reinforcement learning algorithms.

New tool evaluates progress in reinforcement learning

Spectroscopy technology is critical for numerous industries, facilitating precise analysis of physical, chemical, and structural properties through interactions between matter and infrared light. Hamamatsu Photonics introduces the FTIR Engine C16511-01, a state-of-the-art near-infrared spectrometer designed for rapid and accurate data acquisition in demanding industrial environments. Leveraging advanced optical interferometry, Ethernet connectivity, and a compact form factor, this instrument enhances real-time monitoring capabilities in sectors such as pharmaceuticals, food processing, and biotechnology. By addressing previous technological limitations, Hamamatsu’s innovation provides greater accuracy, reliability, and integration flexibility, significantly advancing the application of industrial spectroscopy.<h2>Introduction</h2>Optical spectroscopy is a technique that analyzes how light interacts with matter to determine its physical, chemical, or structural properties using wavelengths in the ultraviolet (UV), visible, or infrared spectrum. Increasingly, spectroscopy is essential in sectors such as pharmaceutical manufacturing, food processing, and biotechnology, where rapid and accurate real-time data acquisition is crucial for quality control and operational efficiency [1]. Responding to these industry demands, Hamamatsu Photonics has released the <a href="https://www.hamamatsu.com/us/en/product/optical-sensors/spectrometers/ftir-engine/C16511-01.html">FTIR Engine C16511-01</a>. It is engineered to overcome limitations of traditional spectrometers, including slow data processing, limited integration flexibility, and inadequate communication interfaces [2].<h3>Current Challenges in Optical Spectroscopy</h3>Traditionally, industrial spectroscopy faced substantial challenges, primarily involving complex instrumentation and limited data transfer speeds. Bulky equipment often cannot fit easily into crowded factory environments. Many traditional systems rely on USB connections, limiting data speed and reliability, which complicates rapid decision-making in industrial production [2]. These industrial diffractive spectrometers also face a critical trade-off between spectral resolution and measurement speed. FTIR spectrometers, however, overcome this compromise, delivering high spectral resolution simultaneously with high-speed data collection [2].Moreover, environmental factors such as temperature variations, vibrations from machinery, and electromagnetic interference can affect optical components. These factors make it challenging to maintain consistently high wavelength accuracy. Precision alignment of mirrors and detectors also poses difficulties over extended operational periods, especially in environments where frequent calibration may be impractical. Uncalibrated measurements become unstable and degrade the quality of collected data, leading to less confident quality control outcomes.Another significant issue is the variability in sample conditions and analyte concentrations, which can demand real-time monitoring. Bulky or sensitive spectrometers may have limited tolerance for environmental fluctuations, necessitating controlled laboratory-like conditions that are not always feasible in process lines [3]. Consequently, industrial facilities experience production slowdowns, higher operational costs, and elevated risk of noncompliant products. When high wavelength accuracy and stable data acquisition are not ensured, results can become inconsistent or erroneous, necessitating rework or scrapped batches, directly impacting a company’s competitiveness [4].In short, the combination of physical hardware constraints, suboptimal communication interfaces, environmental stressors, and calibration complexities can all impede successful spectroscopic analysis [5]. Addressing these limitations is essential for safeguarding product integrity, optimizing resource usage, and enabling effective real-time decision-making in modern industrial ecosystems [1]. <h2>Introducing the FTIR Engine C16511-01</h2>The <a href="https://www.hamamatsu.com/us/en/product/optical-sensors/spectrometers/ftir-engine/C16511-01.html">FTIR Engine C16511-01</a> from Hamamatsu integrates advanced Fourier Transform Infrared (FTIR) technology within a compact, rugged enclosure optimized for industrial applications [1]. By utilizing Ethernet (GigE Vision) connectivity, this new instrument ensures significantly enhanced communication speed and reliability compared to traditional USB-connected spectrometers [1,2].<h3><iframe id="680910fd4f6c9900d9178b4a" width="250" class="specs-iframe" height="440" src="https://wevolver.com/iframe/specs/ftir-engine-ft-nir-spectrometer?iframe=true" frameborder="0" scrolling="no"></iframe>Advanced Optical Interferometer Technology</h3>Central to the FTIR Engine C16511-01 is its Michelson optical interferometer, which includes a built-in light input section, beam splitter, fixed mirror, movable mirror (ϕ3 mm), and a high-performance InGaAs photodetector. This configuration precisely captures variations in light intensity signals caused by the position of the movable mirror. These signals are processed using a Fourier transformation, producing highly accurate optical spectra [1].Additionally, the system features an integrated vertical cavity surface-emitting laser (VCSEL). A VSCEL is a specialized semiconductor laser that emits light perpendicular to the wafer surface, providing continuous, precise monitoring of the movable mirror’s position. This distinctive laser design ensures superior wavelength accuracy and thermal stability by producing a stable and narrow emission profile, which is critical for sensitive industrial processes requiring rigorous quality control. By delivering a consistent reference signal, the VCSEL minimizes measurement drift and enhances the overall precision of Fourier transform calculations, thus maintaining reliable spectral data throughout demanding industrial operations [1].<h2>Detailed Technical Capabilities</h2><h3>High Signal-to-Noise Performance</h3>With a signal-to-noise ratio exceeding 10,000, the device can reliably detect and quantify subtle variations in spectral data. This sensitivity ensures accurate measurements even in environments with inherent background noise, enabling precise detection of low-concentration analytes critical for many industrial processes [1].<h3>High-Speed Data Acquisition</h3>The FTIR Engine C16511-01 records spectra at a rate of 275 frames per second. This capability is crucial for capturing dynamic processes in real-time, essential for rapidly evolving reactions or high-throughput industrial environments where timely data is critical [1].<h3>Ethernet Connectivity</h3>The Ethernet (GigE Vision) interface provides rapid and reliable data transfer, fully compatible with Windows and Linux operating systems, offering easy integration with OEM equipment. It ensures robust, continuous performance even in electromagnetically noisy industrial environments [1,2].<h3>Compact Form Factor</h3>The compact design, measuring 68 × 124 × 66 mm and weighing approximately 580 g, facilitates integration into constrained or mobile industrial settings without sacrificing durability. This form factor enables installation in various operational configurations, including robotic or automated systems, where space efficiency is paramount [1].<h3>High Wavelength Accuracy</h3>The built-in VCSEL laser provides precise positional feedback of the movable mirror, maintaining consistent wavelength accuracy. This capability ensures reliable quantitative and qualitative analyses across multiple measurements, which is critical in regulatory-sensitive applications such as pharmaceuticals and food safety [1].<h3>Broad Spectral Range</h3>Covering wavelengths from 1100 nm to 2500 nm, the FTIR Engine enables comprehensive analysis across a wide variety of chemical compounds. This extensive spectral coverage supports diverse industrial applications, facilitating detailed molecular characterization essential for quality control and research [1].<h3>Versatile Industrial Applications</h3>The FTIR Engine C16511-01 is a versatile analytical tool supporting various industries. In pharmaceuticals, it enables rapid, non-destructive inspection of medicinal products, ensuring accurate identification and quantification of active pharmaceutical ingredients (APIs) and excipients. It also supports polymorphism studies essential for drug solubility, stability, and bioavailability, and quickly detects cross-contamination between production batches, preventing costly disruptions [5,8].Within food processing and agriculture, the engine rapidly authenticates ingredients, detects contaminants, and evaluates nutritional profiles, providing immediate quality assurance. Its non-destructive nature and minimal sample preparation streamline routine testing, ensuring consistency and safety in food production [6,9].Biotechnology industries utilize the FTIR Engine for real-time monitoring of biochemical reactions, gaining valuable insights into reaction dynamics, yield optimization, and purity control. It plays a vital role in downstream processing, verifying protein and enzyme purity, and preventing costly batch failures by identifying deviations early [7,10].Additionally, the FTIR Engine significantly enhances recycling processes by rapidly identifying various polymers such as polyethylene, polypropylene, and polystyrene. Automated inline systems leverage its capabilities for efficient sorting of multi-layer plastics, improving recycling accuracy and supporting sustainable waste management [5,11].<h2>User Benefits and Integration</h2>The FTIR Engine C16511-01 provides significant operational advantages, including high precision and rapid measurements for improved decision-making and quality assurance. Its robust Ethernet connectivity ensures reliable, high-speed data transfer, reducing downtime and maintenance requirements. The compact design simplifies integration across diverse industrial setups, enhancing flexibility.To further support customers, Hamamatsu’s FTIR Engine comes with intuitive evaluation software. This software facilitates streamlined data acquisition, real-time configuration, and spectral visualization. It logs extensive spectral data and supports automated batch processing. Additionally, detailed DLL specifications allow integrators to develop custom software modules using languages such as C++ or Python, tailored to specific analytical needs. These APIs seamlessly integrate with existing SCADA systems and synchronize with third-party sensors or actuators, significantly improving overall process control and operational efficiency [1].<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzQ1NDE3NDYzNjYyLTExQTd3XzZBTHlXN0VzNUJIUTR6b0JsOVFiUnF2QjlhLmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width:833px" class="fr-fic fr-dib" />Connection diagram for transmission measurement.<h2 id="isPasted">Additional Options and Accessories</h2>Hamamatsu offers several accessories that further improve reliability and integration flexibility. Vibration isolation tables ensure measurement stability, specialized optical fiber cables minimize signal distortion, and flexible power options (12 V or 24 V) accommodate diverse industrial requirements. The FTIR Engine is also compatible with the L16462-01, a fiber-coupled diffused reflection light source designed for near-infrared applications. This light source enhances signal collection for diffuse reflectance measurements, improving data quality in in-line or remote monitoring applications. Together, these options ensure consistent data quality in demanding operational conditions [1].<h3>Enhance Your Real-Time Monitoring Capabilities</h3>The FTIR Engine C16511-01 offers high-speed, high-accuracy spectral data acquisition in a compact, industrial-ready design. With advanced optical interferometry, integrated VCSEL technology, and robust Ethernet connectivity, it supports reliable in-line analysis across a range of demanding applications—from pharmaceutical manufacturing to polymer sorting.<a href="https://www.hamamatsu.com/eu/en/product/optical-sensors/spectrometers/ftir-engine/C16511-01.html">Learn more about the FTIR Engine C16511-01 and how it can support your analytical and process control requirements.</a><h2>References</h2>[1] Hamamatsu FTIR Engine C16511-01 Technical Documentation, Hamamatsu Photonics[2] Hamamatsu FTIR Engine C15511-01 Technical Documentation (Previous Version), Hamamatsu Photonics[3] Mitchell, S. (2020). "Calibration complexities in near-infrared reflectance technology for high-throughput lines." Journal of Applied Spectroscopy, 47(1), 11–15.[4] Smith, J. &amp; Wilhelm, K. (2021). "Transmission Bottlenecks in High-Volume Spectral Data Systems." Industrial Engineering Journal, 58(2), 89–97.[5] FTIR Spectroscopy Testing and Analysis, Contract Laboratory: https://outsource.contractlaboratory.com/ftir-spectroscopy-testing-and-analysis[6] Agilent Technologies, FTIR Applications in Food Testing: https://www.agilent.com/library/applications/5991-1246EN_AppNote_MM_FoodIngredients.pdf[7] Mettler Toledo, FTIR Spectroscopy for Bioprocess Monitoring:<a href="https://www.mt.com/us/en/home/applications/L1_AutoChem_Applications/ftir-spectroscopy.html"> https://www.mt.com/us/en/home/applications/L1_AutoChem_Applications/ftir-spectroscopy.html</a>[8] Huang, T., &amp; Carter, S. (2022). "Advancements in FTIR-Based Contamination Detection in Pharmaceutical Manufacturing." Journal of Pharmaceutical Analysis, 34(3), 211–219.[9] Rossi, L., &amp; Martins, J. (2021). "Nutrient Profiling Using FTIR Spectroscopy in Food Production." Food Quality and Safety Journal, 17(4), 98–104.[10] Pérez, M. &amp; Clarkson, D. (2023). "Real-Time Downstream Process Monitoring with FTIR in Biotechnology." Bioprocess Engineering Quarterly, 45(2), 67–72.[11] Tanaka, Y. &amp; Basu, R. (2021). "Automated Inline FTIR Analysis for Multi-Layer Polymer Recycling." Journal of Sustainable Materials Engineering, 22(1), 13–21.

Hamamatsu Photonics introduces the FTIR Engine C16511-01, a state-of-the-art near-infrared spectrometer designed for rapid and accurate data acquisition in demanding industrial environments.

Compact, High-Speed Spectroscopy for Real-Time Applications: The FTIR Engine C16511-01

Data privacy comes with a cost. There are security techniques that protect sensitive user data, like customer addresses, from attackers who may attempt to extract them from AI models — but they often make those models less accurate.MIT researchers recently developed a framework, based on a new privacy metric called PAC Privacy, that could maintain the performance of an AI model while ensuring sensitive data, such as medical images or financial records, remain safe from attackers. Now, they’ve taken this work a step further by making their technique more computationally efficient, improving the tradeoff between accuracy and privacy, and creating a formal template that can be used to privatize virtually any algorithm without needing access to that algorithm’s inner workings.The team utilized their new version of PAC Privacy to privatize several classic algorithms for data analysis and machine-learning tasks.They also demonstrated that more “stable” algorithms are easier to privatize with their method. A stable algorithm’s predictions remain consistent even when its training data are slightly modified. Greater stability helps an algorithm make more accurate predictions on previously unseen data.The researchers say the increased efficiency of the new PAC Privacy framework, and the four-step template one can follow to implement it, would make the technique easier to deploy in real-world situations.“We tend to consider robustness and privacy as unrelated to, or perhaps even in conflict with, constructing a high-performance algorithm. First, we make a working algorithm, then we make it robust, and then private. We’ve shown that is not always the right framing. If you make your algorithm perform better in a variety of settings, you can essentially get privacy for free,” says Mayuri Sridhar, an MIT graduate student and lead author of a <a href="https://eprint.iacr.org/2024/718.pdf" target="_blank">paper on this privacy framework</a>.She is joined in the paper by Hanshen Xiao PhD ’24, who will start as an assistant professor at Purdue University in the fall; and senior author Srini Devadas, the Edwin Sibley Webster Professor of Electrical Engineering at MIT. The research will be presented at the IEEE Symposium on Security and Privacy.<h2>Estimating noise</h2>To protect sensitive data that were used to train an AI model, engineers often add noise, or generic randomness, to the model so it becomes harder for an adversary to guess the original training data. This noise reduces a model’s accuracy, so the less noise one can add, the better.PAC Privacy automatically estimates the smallest amount of noise one needs to add to an algorithm to achieve a desired level of privacy.The original PAC Privacy algorithm runs a user’s AI model many times on different samples of a dataset. It measures the variance as well as correlations among these many outputs and uses this information to estimate how much noise needs to be added to protect the data.This new variant of PAC Privacy works the same way but does not need to represent the entire matrix of data correlations across the outputs; it just needs the output variances.“Because the thing you are estimating is much, much smaller than the entire covariance matrix, you can do it much, much faster,” Sridhar explains. This means that one can scale up to much larger datasets.Adding noise can hurt the utility of the results, and it is important to minimize utility loss. Due to computational cost, the original PAC Privacy algorithm was limited to adding isotropic noise, which is added uniformly in all directions. Because the new variant estimates anisotropic noise, which is tailored to specific characteristics of the training data, a user could add less overall noise to achieve the same level of privacy, boosting the accuracy of the privatized algorithm.<h2>Privacy and stability</h2>As she studied PAC Privacy, Sridhar hypothesized that more stable algorithms would be easier to privatize with this technique. She used the more efficient variant of PAC Privacy to test this theory on several classical algorithms.Algorithms that are more stable have less variance in their outputs when their training data change slightly. PAC Privacy breaks a dataset into chunks, runs the algorithm on each chunk of data, and measures the variance among outputs. The greater the variance, the more noise must be added to privatize the algorithm.Employing stability techniques to decrease the variance in an algorithm’s outputs would also reduce the amount of noise that needs to be added to privatize it, she explains.“In the best cases, we can get these win-win scenarios,” she says.The team showed that these privacy guarantees remained strong despite the algorithm they tested, and that the new variant of PAC Privacy required an order of magnitude fewer trials to estimate the noise. They also tested the method in attack simulations, demonstrating that its privacy guarantees could withstand state-of-the-art attacks.“We want to explore how algorithms could be co-designed with PAC Privacy, so the algorithm is more stable, secure, and robust from the beginning,” Devadas says. The researchers also want to test their method with more complex algorithms and further explore the privacy-utility tradeoff.“The question now is: When do these win-win situations happen, and how can we make them happen more often?” Sridhar says.“I think the key advantage PAC Privacy has in this setting over other privacy definitions is that it is a black box — you don’t need to manually analyze each individual query to privatize the results. It can be done completely automatically. We are actively building a PAC-enabled database by extending existing SQL engines to support practical, automated, and efficient private data analytics,” says Xiangyao Yu, an assistant professor in the computer sciences department at the University of Wisconsin at Madison, who was not involved with this study.This research is supported, in part, by Cisco Systems, Capital One, the U.S. Department of Defense, and a MathWorks Fellowship.

MIT researchers enhanced a data privacy technique so it is more computationally efficient and increases the accuracy of the AI algorithms to which it is applied. Image: MIT News; iStock

The approach maintains an AI model’s accuracy while ensuring attackers can’t extract secret information.

New method efficiently safeguards sensitive AI training data

Researchers from TU/e have transmitted data between the TU/e campus and the High Tech Campus over a 4.6 km distance using infrared light. This happened at the astonishing rate of 5.7 terabits per second, the equivalent of streaming 1.9 million Netflix shows in HD simultaneously. This is the fastest wireless data transmission ever demonstrated over this big a distance in an urban setting.The <a href="https://arxiv.org/pdf/2503.21058" target="_blank" rel="noreferrer">record-breaking connection</a> was established between TU/e in the north and the High Tech Campus (HTC) in the south of Eindhoven using advanced optical antennas from Aircision, a spin-off of TNO that develops products for ultra-high capacity optical wireless systems. The company is located at the HTC.Their antennas transmit data through invisible infrared beams instead of cables or radio signals. This technique, known as free-space optical (FSO) communication, enables ultra-fast, interference-free data transmission.Infrared wireless communication combines the high data speeds known from optical fibers with the flexibility of wireless communication systems.Vincent van Vliet, PhD researcher“We need new ways to meet the increasing demand for fast and reliable connectivity,” says <a href="https://research.tue.nl/nl/persons/vincent-van-vliet" target="_blank" rel="noreferrer">Vincent van Vliet</a>, a TU/e PhD researcher involved in the project.<h3>Breaking boundaries in wireless speed </h3>“Infrared wireless communication combines the high data speeds known from optical fibers with the flexibility of wireless communication systems. By complementing existing wireless and fiber-optic technologies, we can build the densely interconnected networks required to bring high-speed data connectivity to every corner of the planet.”<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1744719540053-csm_BvOF+2023_0426_ABA+-+HCOT+lab_338cf0c9ed.jpg" style="width:100%px" class="fr-fic fr-dib" />Vincent van Vliet working in the laboratory. Photo: Bart van OverbeekeTo achieve this breakthrough, the team used the Reid Photonloop testbed. The TU/e has launched this permanent set-up to experiment with high-speed wireless communication. It uses cutting-edge technology that combines multiple wavelengths in a single transmission. This technique, commonly used in fiber optics, has now been successfully applied to transmit data with this high speed over this big a distance for the first time in urban wireless communication.“Because the transmitted infrared light is highly focused, an almost unlimited number of communication links can exist side-by-side without interference, allowing wireless network capacity growth at an unprecedented scale”, Van Vliet explains.<h3>A permanent test facility for next-gen networks  </h3>One end of the Reid Photonloop is located on the top of the Flux building of the TU/e campus, which houses the departments of <a href="https://www.tue.nl/en/our-university/departments/electrical-engineering" target="_blank">Electrical Engineering</a> and <a href="https://www.tue.nl/en/our-university/departments/applied-physics-and-science-education" target="_blank">Applied Physics and Science Education</a>. The other end of the test bed, 4.6 kilometers away on the other side of the city of Eindhoven, sits at the top of building 37 at the High Tech CampusThe findings were presented at the Optical Fiber Communications (OFC) Conference 2025 in San Francisco earlier this month.<a href="https://www.tue.nl/en/research/researchers/chigo-okonkwo" target="_blank">Chigo Okonkwo</a>, Associate Professor and head of TU/e’s High-Capacity Optical Transmission Lab, emphasizes the importance of the testbed. “This facility will allow us to refine high-speed wireless communication and optimize its reliability and availability in all weather conditions”, he says.<h3>Real-life deployments</h3><a href="https://www.aircision.com/" target="_blank" rel="noreferrer">Aircision</a> is already looking at how this technology can be used in real-world applications, such as wirelessly connecting new 5G/6G antennas for backhauling the existing network to bring high-speed internet access to areas where laying fiber is impractical or too costly.Luis Oliveira, co-founder of Aircision, is optimistic: “We are redefining how data is transmitted over the air. This record-breaking achievement proves that our technology is ready to make high-speed internet accessible to millions of people faster than ever before.”The Reid Photonloop testbed is named after the late Aircision co-founder John Reid, who was a driving force behind the development of the test bed but passed away before it was realized. The work is funded by the NWO TTW-Perspectief FREE P19-13, PhotonDelta National Growth Fund Programme on Photonics, and European Innovation Council Transition project CombTools (G.A. 101136978).<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1744719610593-csm_Bob_102+copy_974fef770f.jpg" style="width:100%px" class="fr-fic fr-dib" /><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1744719617319-csm_Bob_17+copy+2_b45e73756c.jpg" style="width:100%px" class="fr-fic fr-dib" />

The optical antenna on the Flux roof overlooking Eindhoven, facing the direction of the High Tech Campus. Photo: Vincent van Vliet

TU/e researchers have sent the equivalent of 1.9 million Netflix series via infrared light from the roof of their building.

Invisible beams of light provide super-fast wireless data transfer

Today, almost everybody has heard of AI and millions around the world already use, or are exposed, to it - from ChatGPT writing our emails, to helping in medical diagnosis.At its base, AI uses algorithms – sets of mathematically rigorous instructions - that tell a computer how to perform a variety of advanced functions or transform facts into useful information. The Large Language Models (LLMs), that drive today’s increasingly powerful AI, are special kinds of algorithms that learn from massive, mostly centralized datasets.Yet, centralizing these huge datasets generates issues around security, privacy and the ownership of data – indeed the phrase ‘data is the new oil’ signifies that it has become a crucial resource, driving innovation and growth in today’s digital economy.To counter these concerns, an approach called federated learning is now revolutionizing AI. Contrary to training AI models on huge, centralized datasets, federated learning allows these models to learn across a network of decentralized devices (or servers), keeping the raw data at its source.<h2>Untrusting Data</h2>“Today’s AI trained with federated learning gathers data from all over the world – the internet, other large databases, hospitals, smart devices and so on. These systems are very effective but at the same time there’s a paradox. What makes them so effective also makes them very vulnerable to learning from ‘bad’ data,” explains Professor <a href="https://dcl.epfl.ch/rachid/">Rachid Guerraoui</a>, Head of the <a href="https://dcl.epfl.ch/site/">Distributed Computing Laboratory</a> (DCL) in the <a href="https://www.epfl.ch/schools/ic/">School of Computer and Communication Sciences</a>.Data can be bad for many reasons. Perhaps a lack of attention or human error means it is incorrectly entered into a database, maybe there are mistakes in the data to begin with, perhaps sensors or other instruments are broken or malfunctioning, incorrect or dangerous data may be recorded maliciously, etc. Sometimes, the data is good but the machine hosting it is hacked or bogus. In any case, if this data is used to train AI, it makes the systems less trustworthy and unsafe.“All this brings up one key question,” says Guerraoui, “can we build trustworthy AI systems without trusting any individual source of data?” After a <a href="https://dcl.epfl.ch/site/safeai">decade of theoretical work</a> dedicated to addressing this challenge, the professor and his team say the answer is yes! A <a href="https://link.springer.com/book/10.1007/978-981-97-0688-4" target="_blank" rel="noopener">recent book</a> summarizes their main findings.<h2>Trusting Datasets</h2>In collaboration with the <a href="https://www.inria.fr/en" target="_blank" rel="noopener">French National Institute for Research in Digital Science and Technology</a>, they are now putting their ideas to work. They have developed <a href="https://actu.epfl.ch/news/trustworthy-ai-without-trusted-data/byzfl.epfl.ch">ByzFL</a>, a library using the Python programming language that is designed to benchmark, and improve, federated learning models against adversarial threats, particular bad data.“We believe that the majority of data is good but how do we know which datasets we can’t trust?” asks Guerraoui. “Our ByzFL library tests whether a system is robust against priori unknown attacks and then makes that system more robust. More specifically, we give users software to emulate bad data for testing as well as including security filters to ensure robustness. The bad data is often distributed in a subtle way so that it’s not immediately visible.”ByzFL doesn’t isolate and locate good from bad data but uses robust aggregation schemes (e.g., median) to ignore extreme inputs. For example, if three sensors record a temperature of 6, 7 and 9 degrees but another records -20, it ruins an entire computation. The ByzFL software excludes the extremes so that the impact of the bad data is limited, while information is aggregated.<h2>Ensuring that next-generation AI works</h2>Artificial intelligence is expected to touch every part of our lives in the not too distant future. Guerraoui argues that today, most companies use very primitive forms of AI, for example streaming platforms recommending movies or AI assistants helping to write text. If someone doesn’t like the movie they are recommended or an email isn’t perfect it’s no big deal.Looking ahead, for any application that is mission critical, such as diagnosing cancer, driving a car or controlling an aeroplane, safe AI is essential. “The day that we really put Generative AI in hospitals, cars or transport infrastructure I think we will see that safety is problematic because of bad data,” Guerraoui says. “The biggest challenge right now is going from what I call an animal circus to the real world with something that we can trust. For critical applications, we are far from the point where we can stop worrying about safety. The goal of ByzFL is to help bridge this gap.”<h2>A role for Switzerland</h2>The professor worries that it may take some big accidents for the public and policy makers to understand that the AI created to date shouldn’t be used for medicine, transport or anything mission critical and that the development of a new generation of safe and robust AI is essential.“I think Switzerland can play a role here because we have a tradition of seriousness. We build things that work, we can use the guarantee of Swiss quality to demonstrate a certification system using this kind of software to show that AI really is safe without trusting any individual component,” he concluded.ByzFL was designed and developed by John Stephen, <a href="https://www.linkedin.com/in/geovani-rizk/" target="_blank" rel="noopener">Geovani Rizk</a>,<a href="https://www.linkedin.com/in/marc-gonzalez-vidal-786681201/" target="_blank" rel="noopener">Marc Gonzalez Vidal</a>,<a href="https://www.linkedin.com/in/rafael-pinot-61a477bb/" target="_blank" rel="noopener">Rafael Pinot</a>,<a href="https://dcl.epfl.ch/rachid/">Rachid Guerraoui</a> (all from EPFL) and <a href="https://www.linkedin.com/in/francois-taiani-445a1027/" target="_blank" rel="noopener">Francois Taiani</a> (from INRIA).Mehdi El Mhamdi, Julian Steiner, Peva Blanchard, Nirupam Gupta, Rafael Pinot, Youssef Allouah, Abdellah El Mrini, John Stephan, Sadegh Farhadkhani, Geovani Rizk, Arsany Guiguis, Georgios Damaskinos, Sebastien Rouault, Richeek Patra, Mahsa Taziki, Hoang Le Nguyen and Alexandre Maurer are all students and postdocs who have all worked with Professor Guerraoui in the challenge of trustworthy AI systems without trusted data.

EPFL researchers developed a ground-breaking new tool to help build safer AI.

Trustworthy AI without Trusted Data

The use of terahertz waves, which have shorter wavelengths and higher frequencies than radio waves, could enable faster data transmission, more precise medical imaging, and higher-resolution radar.But effectively generating terahertz waves using a semiconductor chip, which is essential for incorporation into electronic devices, is notoriously difficult.Many current techniques can’t generate waves with enough radiating power for useful applications unless they utilize bulky and expensive silicon lenses. Higher radiating power allows terahertz signals to travel farther. Such lenses, which are often larger than the chip itself, make it hard to integrate the terahertz source into an electronic device.To overcome these limitations, MIT researchers developed a terahertz amplifier-multiplier system that achieves higher radiating power than existing devices without the need for silicon lenses.By affixing a thin, patterned sheet of material to the back of the chip and utilizing higher-power Intel transistors, the researchers produced a more efficient, yet scalable, chip-based terahertz wave generator.This compact chip could be used to make terahertz arrays for applications like improved security scanners for detecting hidden objects or environmental monitors for pinpointing airborne pollutants.“To take full advantage of a terahertz wave source, we need it to be scalable. A terahertz array might have hundreds of chips, and there is no place to put silicon lenses because the chips are combined with such high density. We need a different package, and here we’ve demonstrated a promising approach that can be used for scalable, low-cost terahertz arrays,” says Jinchen Wang, a graduate student in the Department of Electrical Engineering and Computer Science (EECS) and lead author of a paper on the terahertz&nbsp;radiator.He is joined on the paper by EECS graduate students Daniel Sheen and Xibi Chen; Steven F. Nagle, managing director of the T.J. Rodgers RLE Laboratory; and senior author Ruonan Han, an associate professor in EECS, who leads the Terahertz Integrated Electronics Group. The research will be presented at the IEEE International Solid-States Circuits Conference.<h2>Making waves</h2>Terahertz waves sit on the electromagnetic spectrum between radio waves and infrared light. Their higher frequencies enable them to carry more information per second than radio waves, while they can safely penetrate a wider range of materials than infrared light.One way to generate terahertz waves is with a CMOS chip-based amplifier-multiplier chain that increases the frequency of radio waves until they reach the terahertz range. To achieve the best performance, waves go through the silicon chip and are eventually emitted out the back into the open air.But a property known as the dielectric constant gets in the way of a smooth transmission.The dielectric constant influences how electromagnetic waves interact with a material. It affects the amount of radiation that is absorbed, reflected, or transmitted. Because the dielectric constant of silicon is much higher than that of air, most terahertz waves are reflected at the silicon-air boundary rather than being cleanly transmitted out the back.Since most signal strength is lost at this boundary, current approaches often use silicon lenses to boost the power of the remaining signal.&nbsp;The MIT researchers approached this problem differently.They drew on an electromechanical theory known as matching. With matching, they seek to equal out the dielectric constants of silicon and air, which will minimize the amount of signal that is reflected at the boundary.They accomplish this by sticking a thin sheet of material which has a dielectric constant between silicon and air to the back of the chip. With this matching sheet in place, most waves will be transmitted out the back rather than being reflected.<h2>A scalable approach</h2>They chose a low-cost, commercially available substrate material with a dielectric constant very close to what they needed for matching. To improve performance, they used a laser cutter to punch tiny holes into the sheet until its dielectric constant was exactly right.“Since the dielectric constant of air is 1, if you just cut some subwavelength holes in the sheet, it is equivalent to injecting some air, which lowers the overall dielectric constant of the matching sheet,” Wang explains.In addition, they designed their chip with special transistors developed by Intel that have a higher maximum frequency and breakdown voltage than traditional CMOS transistors.“These two things taken together, the more powerful transistors and the dielectric sheet, plus a few other small innovations, enabled us to outperform several other devices,” he says.Their chip generated terahertz signals with a peak radiation power of 11.1 decibel-milliwatts, the best among state-of-the-art techniques. Moreover, since the low-cost chip can be fabricated at scale, it could be integrated into real-world electronic devices more readily.One of the biggest challenges of developing a scalable chip was determining how to manage the power and temperature when generating terahertz waves.“Because the frequency and the power&nbsp;are so high, many of the standard ways to design a CMOS chip are not applicable here,” Wang says.The researchers also needed to devise a technique for installing the matching sheet that could be scaled up in a manufacturing facility.Moving forward, they want to demonstrate this scalability by fabricating a phased array of CMOS terahertz sources, enabling them to steer and focus a powerful terahertz beam with a low-cost, compact device.<hr>This research is supported, in part, by NASA’s Jet Propulsion Laboratory and Strategic University Research Partnerships Program, as well as the MIT Center for Integrated Circuits and Systems. The chip was fabricated through the Intel University Shuttle Program.

By affixing a thin, patterned sheet of material to the back of the chip, highlighted in the center and shown in the left-side micrograph, the researchers produced a more efficient, yet scalable, chip-based terahertz wave generator. Image: Courtesy of the researchers; MIT News

Researchers developed a scalable, low-cost device that can generate high-power terahertz waves on a chip, without bulky silicon lenses.

Chip-based system for terahertz waves could enable more efficient, sensitive electronics

The AI revolution has ushered in an era of exponential power and energy consumption. According to the <a href="https://www.energy.gov/articles/doe-releases-new-report-evaluating-increase-electricity-demand-data-centers" rel="noopener" target="_blank">US Department of EnergyOpens in new window</a>, energy consumed by AI data centers could triple by 2028. Today, up to 40% of data center power use comes from cooling high-power chips—an astounding amount equivalent to the state of California’s entire electricity consumption.To combat this, Sheng Shen, professor of mechanical engineering at Carnegie Mellon University, has developed an innovative thermal interface material (TIM) that outperforms existing state-of-the-art solutions. His design, now published in <a href="https://www.nature.com/articles/s41467-025-56163-8" rel="noopener" target="_blank">Nature CommunicationsOpens in new window</a>, achieves ultra-low thermal resistance while increasing cooling efficiency via improved heat dissipation. It also proves to be highly reliable.<blockquote>While an immediate need is cooling data centers, this innovation can break through in industries that have been stuck using outdated thermal interface materials.<cite>Sheng Shen, Professor, Mechanical Engineering</cite></blockquote>“The material is like a bridge between the nano- and macroscopic worlds,” explained Zexiao Wang, Ph.D. candidate in Shen’s lab. “Because the nanoscale material can be created using macroscale approaches, we can see with our own eyes the impact of the material on the world.”Not only is Shen’s thermal interface material the best-performing on the market, it is also highly reliable. The team tested the material at extreme temperature ranges from -55 to 125 degree Celsius for more than 1,000 cycles, and the material showed no performance degradation.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1740445088809-0211-em-ai-data-center-cooling-breakthrough.png" style="width: 100%px;" class="fr-fic fr-dib">Novel thermal interface material designed by Sheng Shen.&nbsp;Source:&nbsp;College of Engineering“This material solves a lot of existing challenges, and is ready to be used today,” said Shen. “While an immediate need is focused on cooling data centers, the application for this innovation is extensive. It can break through in industries that have been stuck using outdated thermal interface materials. It can be used for pre-packaging, reworked when using non-adhesives, and enables thermal bonding of two substrates at room temperature.”“Oftentimes work at the nanoscale is foundational for a device that we might not see for decades,” said Qixian Wang, Ph.D. candidate. “It’s been exciting to see the real-world impact our material can have today because it is so easy to use.”“Our material will have great benefits to the field of AI computing,” said Rui Cheng, postdoc and innovation commercialization fellow of CMU and the lead author of the paper published in Nature Communications. “Beyond reducing energy consumption, we can make AI development more affordable, more renewable, and more reliable.”<iframe width="640" height="360" src="https://www.youtube.com/embed/BG4Ct4jYh3k?&amp;wmode=opaque&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe>This research was supported by the National Science Foundation and ARPA-E (Advanced Research Projects - Energy). Collaborators included Tianyi Chen and Ana V. Garcia-Caraveo from the Oregon State University, and Navid Kazem and Loren Russell from Arieca, Inc.<hr>Sheng Shen and Rui Cheng are making this technology commercially available via their startup company,&nbsp;<a href="https://www.novolinc.com/" rel="noopener" target="_blank">NovoLINC, Inc.Opens in new window</a>

big data

Latest Posts