Gaetano's paper on Scaling Security Testing by Adressing the Reachability Gap has been accepted at #ICSE26! 📝 gpsapia.github.io/files/ICSE_2... 🧑‍💻 github.com/GPSapia/Reac... How to scale automatic security testing to arbitrary systems?

This is the eXplainable AI research channel of the machine learning group of Prof. Klaus-Robert Müller at Technische Universität Berlin @tuberlin.bsky.social & BIFOLD @bifold.berlin. Let's connect! #XAI #ExplainableAI #MechInterp #MachineLearning #Interpretability

Congratulations to Dr. Jonas Dippel on successfully defending his doctoral dissertation titled “Towards Robust Generalizable Machine Learning Models for Computational Pathology.” @tuberlin.bsky.social

On Wednesday, November 5th, as part of our KASTEL Distinguished Lecture Series Prof. Gianluca Stringhini, PhD from Boston University will talk about ‘Improving the Moderation of False Information and Influence Campaigns on Social Media’. Everybody is welcome and stay around for the Q&A afterwards.

Today I turn 60 – and what a journey this has been! Grateful for family, friends, students, colleagues, and a scientific community that keeps me inspired. The big party? You’ll have to wait four years, when I hit my (binary) 1,000,000th birthday. 😉

You prefer to organize your workshop in Europe? We've got you covered! We extended the call for workshops at EuroS&P 2026 to give you a few more days to make the move 😎 See you in Lisbon 🇵🇹 🌐 https://eurosp2026.ieee-security.org/cfw.html ⏱️ Deadline: Oct 2̶4̶t̶h̶ 30th AoE 📍Lisbon, PT

Had a great time visiting @darpsky.bsky.social at Technische Universität Wien last week. It's exciting to see him build up his new group! Many thanks to the whole Security & Privacy research unit for the welcoming atmosphere and interesting discussions!

70% fail the final exam. 60% fail the retake. Less than half pass. Our intro programming course numbers – not unique. The disturbing part? By Week 4, students know they can’t program. Four months later: still can’t. Nothing changed. Why? uni-mal-anders.de/en/shorts/20...

"AI predicts rain. We predict trouble!" The BIFOLD paper was recognized with a Distinguished Paper Award at the ACM Conference on Computer and Communications Security (CCS) www.bifold.berlin/news-events/... #MLSky #cybersecurity #Meteorology #ClimateScience #AIForScience #AIWeather #SecureAI

AI predicts rain. We predict trouble! Today, Erik presents a novel attack on Google's latest AI weather model at #CCS2025. By changing only 0.1% of the observations, the attack can fabricate or suppress the prediction of extreme events, from hurricanes 🌀 to heat waves 🔥 1/4 @bifold.berlin

Exposing Security Risks in AI Weather Forecasting Erik Imgrund of the MLSEC group ( @rieck.mlsec.org ) will present the paper “Adversarial Observations in Weather Forecasting” at ACM CCS. t1p.de/6k0uc #MLsky #cybersecurity #ML #research #AI @tuberlin.bsky.social

We are pleased to announce that BIFOLD Co-Director Prof. Dr. Klaus-Robert Müller has been awarded the 2026 Neural Network Pioneer Award by the IEEE Computational Intelligence Society. www.bifold.berlin/news-events/... #MLSky #IEEECommunity #AI #science #SciComm #ML @tuberlin.bsky.social #ieee

Better AI tools, worse exam results. No paradox – it’s externalization of thinking. Failure rates rising at my uni for 2 semesters. Colleagues report 65-78% fail rates. Students are becoming passengers in their own education. My new blog series 👇Thread below. uni-mal-anders.de/en/shorts/20...

After 5 years, we are back at NDSS in San Diego! Looking forward to submissions from the Security and the Software Engineering community!

📢 CFP for DIMVA 2026 is out! First deadline: 03 December 2025. Daniele Cono D'Elia and I look forward to your submissions! dimva.org/dimva2026/ If you would like to serve on the PC, do not forget to fill in the (self-) nomination form, lnkd.in/dRQ48dH7 RTs appreciated! 🙌

Tagesspiegel named Dr. Stefan Chmiela among Berlin’s 100 most important minds in science 2025. www.bifold.berlin/news-events/... @tuberlin.bsky.social @tagesspiegel.de #MLsky

#Chatkontrolle verhindern Die EU-Kommission plant eine Verordnung, die Anbieter von Messenger-Diensten. E-Mail-Providern und anderen Kommunikationsdiensten verpflichten würde, private Nachrichten automatisiert zu durchsuchen und strafbare Inhalte zu melden. [1/x] netzpolitik.org/2025/interne...

We are alarmed by reports that Germany is on the verge of a catastrophic about-face, reversing its longstanding and principled opposition to the EU’s Chat Control proposal which, if passed, could spell the end of the right to privacy in Europe. signal.org/blog/pdfs/ge...

🗣️ Call for Papers – #DIMVA26 Deadlines are out! 📅Cycle 1 is Dec 3. CfP is live 👉 dimva.org/dimva2026 📍 Chania, Greece | 1–3 July 2026 Don’t miss your chance to share your research! #CFP

After having pointed out severe shortcomings of existing XAI paradigms and feature attribution methods in the past, I am happy to announce two novel methodological contributions, to be presented in this year's main track of the premier ML conference, NeurIPS. See LinkedIn post: tinyurl.com/25vu5xsm

GUIFuzz++ is the first general-purpose fuzzer for desktop GUI software! Fuzzing by translating AFL++ random input into user interaction with GUIs, leading to the discovery of 23 new bugs! Paper: futures.cs.utah.edu/papers/25ASE.pdf Source: github.com/FuturesLab/GUIFuzzPlusPlus Go test some GUIs!

We’re excited to announce this year’s competitions for @satml.org 🎉 Get ready for four challenges tackling AI in space, backdoors in LLMs, CTF agents, and privacy-preserving databases. satml.org/competitions/ Let’s dive in! 🧵1/5

Did AI folks not value your security insights or vice versa? Maybe you’re submitting your papers to the wrong conference. @satml.org has you covered! We are eager to read your work on the security, privacy, and fairness of AI. 👉 satml.org/call-for-pap... ⏰ Deadline: Sep 24

Many of us assume that clicking “blur” or activating a virtual background protects our privacy. This research shows: that belief is misleading. The safest option is still the simplest one: prepare your real environment for calls instead of relying solely on digital masking.

Study: Seeing through: Analyzing and Attacking Virtual Backgrounds in Video Calls Felix Weißberg, Jan-Malte Hilgefort, Steve Grogorick, Daniel Arp, Thorsten Eisenhofer, Martin Eisemann, Konrad Rieck. Proceedings of the 34th USENIX Security Symposium, 2025. @tuberlin.bsky.social @tuwien.at

The team developed an attack that exposed 53% more background pixels than previous methods, showing just how much information can unintentionally slip through.

These fragments are often invisible to the human eye, but when collected over time, they can be used to reconstruct rooms and even identify personal objects.

Virtual backgrounds leak tiny image fragments of the real environment – so-called pixel leaks. These fragments are often invisible to the human eye, but when collected over time, they can be used to reconstruct rooms and even identify personal objects.

The “digital curtain” in video calls has holes – with the right techniques, people can see through. New MLSec study (BIFOLD) reveals that virtual backgrounds in video conferencing tools are not a reliable privacy shield. t1p.de/ndqxt #ML #Security #Cybersecurity #IT #Study @rieck.mlsec.org

Got some hot research cooking? 🔥 The @satml.org paper deadline is just 9 days away. We are looking forward to your work on security, privacy, and fairness in machine learning. 👉 satml.org/call-for-pap... ⏰ Sep 24

Whoa. 100 responses from speakers at CHES, and only one is presenting by video. Maybe their conference is actually worth going to?

Three weeks to go until the SaTML 2026 deadline! ⏰ We look forward to your work on security, privacy, and fairness in AI. 🗓️ Deadline: Sept 24, 2025 We have also updated our Call for Papers with a statement on LLM usage, check it out: 👉 satml.org/call-for-pap... @satml.org

Trump admin planning to change student visas from lasting for duration of academic program to fixed 4-yr term, and then much harder to renew Could destroy US ability to attract global talent, particularly those seeking advanced degrees in STEM. The median time to complete a PhD is 5.7 yrs per NSF.

📣 Researchers in AI security, privacy & fairness: It's time to share your latest work! The SaTML 2026 submission site is live 👉 hotcrp.satml.org 🗓️ Deadline: Sept 24, 2025 @satml.org

LLM-powered code assistants might suggest vulnerable code to specific user groups. Old news? Well, in contrast to prior attacks of this kind, our "Generalized Adversarial Code Suggestions" (AsiaCCS 2025) impose no restrictions on the vulnerabilities. 🌐 https://intellisec.de/research/adv-code (1/3)

Just noticed my "Julia for Machine Learning" course got 2^8 stars on GitHub, yay! 🎉 github.com/adrhill/juli...

Today I have a more serious topic than usual, please consider reposting for reach: My wife and I are urgently looking for a specialist in neuropediatrics or a similar field for our autistic child with a diagnosed, but not further specified, movement disorder [1/4]

Phrack turns 40. The digital drop is live. Download it. Archive it. Pass it on. 💾 www.phrack.org #phrackat40 #phrack72

Congratulations to Sebastian Baunsgaard successfully defending his PhD thesis, "Workload-aware Compressed Linear Algebra for Data-centric Machine Learning Pipelines" Sebastian is part of the DAMS group (lead: @matthiasboehm7.bsky.social) BIFOLD / @tuberlin.bsky.social #phd #defended

Congratulations to Dr. Dimitrios Giouroukis on defending his PhD "Adaptive Sensor Data Management", supervised by Prof. Dr. Volker Markl at the DIMA Group. #PhDDefense #DataManagement #SensorData @tuberlin.bsky.social

🚨 Got a great idea for an AI + Security competition? @satml.org is now accepting proposals for its Competition Track! Showcase your challenge and engage the community. 👉 satml.org/call-for-com... 🗓️ Deadline: Aug 6

🎉 Congratulations to BIFOLD researchers Simon Letzgus, Klaus-Robert Müller, and Grégoire Montavon on receiving the Best Paper Award at the 3rd World Conference on eXplainable Artificial Intelligence (hashtag#XAI2025). www.bifold.berlin/news-events/... @tuberlin.bsky.social

Today, Jonas presents a new type of adversarial examples at @icmlconf.bsky.social! We exploit subtle numerical differences between linear algebra backends and craft inputs that yield different predictions from the same model depending on the backend used 🤯 mlsec.org/docs/2025-ic... 1/4

NeurIPS is endorsing EurIPS, an independently-organized meeting which will offer researchers an opportunity to additionally present NeurIPS work in Europe concurrently with NeurIPS. Read more in our blog post and on the EurIPS website: blog.neurips.cc/2025/07/16/n... eurips.cc

We’re happy to announce the Call for Competitions for @satml.org The competition track has been a highlight of SaTML, featuring exciting topics and strong participation. If you’d like to host one for SaTML 2026, visit: 👉 satml.org/call-for-com... ⏰ Deadline: Aug 6

Practicing for my plan B career

🚀 NebulaStream is now Open Source! NebulaStream is an Extensible, High-Performance Streaming Engine for Multi-Modal Edge Applications. This novel stream processing engine analyzes sensor data in real time. Now freely available under the Apache 2.0 license. www.bifold.berlin/news-events/...

We're excited to announce the Call for Papers for SaTML 2026, the premier conference on secure and trustworthy machine learning @satml.org We seek papers on secure, private, and fair learning algorithms and systems. 👉 satml.org/call-for-pap... ⏰ Deadline: Sept 24

Thank you senator Katharina Günther-Wünsch, Senatsverwaltung für Bildung, Jugend und Familie, for taking the time to visit the BIFOLD booth at LNdW 2025. We believe that AI education belongs in schools and we try to get the next generation of scientists interested in AI research at an early stage.

Thrilled to share a recent opinion piece at the IEEE Security and Privacy (Vol. 23, Issue 3). Basically a long-term perspective on the field meant for both researchers and practitioners. 📝 ieeexplore.ieee.org/stamp/stamp....