Sign in

Konrad Rieck 🌈

@rieck.mlsec.org
412 followers 114 following 46 posts

Machine Learning and Security, Professor of Computer Science at TU Berlin,

PostsRepliesMedia
Konrad Rieck 🌈 @rieck.mlsec.org · 18/04/2026
Yesterday, Lukas presented at #ICSE2026 results I didn't believe when he first showed them to me. A classifier based on simple code metrics matches frontier LLMs for vulnerability discovery in performance, as long as they are not agentic. 🧵 (1/4)
Paper: LLM-based Vulnerability Discovery through the Lens of Code Metrics
1112
Konrad Rieck 🌈 @rieck.mlsec.org · 15/10/2025
Our attack injects tiny perturbations into the measurements that cause GenCast, the currently best AI weather model by Google, to predict false extreme events. The required changes are so low that they fall within the natural noise of observations and are hard to detect. 3/4
Predicted storm path of Hurricane Katrina
130
Konrad Rieck 🌈 @rieck.mlsec.org · 15/10/2025
Some background: Current weather forecasts largely rely on observations from satellites 🛰️. Around 100 of them orbit Earth, operated by different countries. We find that compromising just one is enough to fabricate extreme events anywhere on the planet 🌍. 2/4
Location of satellite observations and grid points for a prediction step.
110
Konrad Rieck 🌈 @rieck.mlsec.org · 15/10/2025
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
Predicted temperature at the peak of the European Heat Wave 2006
2215
Konrad Rieck 🌈 @rieck.mlsec.org · 19/09/2025
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
SATML Deadline: Sep 24
000
Konrad Rieck 🌈 @rieck.mlsec.org · 15/09/2025
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
053
Konrad Rieck 🌈 @rieck.mlsec.org · 03/09/2025
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
IEEE Conference on Secure and Trustworthy Machine Learning
Technical University of Munich, Germany
March 23–25, 2026
044
Konrad Rieck 🌈 @rieck.mlsec.org · 30/07/2025
🚨 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
052
Konrad Rieck 🌈 @rieck.mlsec.org · 17/07/2025
Technically, we build on the non-associativity of floating-point arithmetic. When computing convolutions or matrix multiplications, the backends split data into blocks and process them in different orders, introducing slight deviations and exposing an attack surface. 2/4
Visualization of a matrix mutplication. The matrices are decomposed into blocks that are processed individually.
120
Konrad Rieck 🌈 @rieck.mlsec.org · 17/07/2025
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
Visualization of the attack. A dog is shown for which three backends yield the prediction "boxer", while one backend returns "castle".
2124
Konrad Rieck 🌈 @rieck.mlsec.org · 07/07/2025
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
Call for Competitions
Competition proposal deadline: August 6, 2025
Decision notification: August 27, 2025
052
Konrad Rieck 🌈 @rieck.mlsec.org · 01/07/2025
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
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), March 23-25, 2025, Munich

Submission deadline: September 24, 2025
062
Konrad Rieck 🌈 @rieck.mlsec.org · 10/04/2025
Great to be at @satml.org with several members of my team from @bifold.berlin and @tuberlin.bsky.social. We are having a blast with exciting discussions and talks on trustworthy AI! #SaTML25
Members of the MLSEC team (mlsec.org)
1153
Konrad Rieck 🌈 @rieck.mlsec.org · 09/04/2025
Full house at #SaTML25! Great to see so many from the secure and trustworthy machine learning community gathered in Copenhagen. @satml.org
Audience at SaTML 2025
071
Konrad Rieck 🌈 @rieck.mlsec.org · 03/03/2025
No plans for April 9–11 yet? — Why not spend an amazing week in beautiful Copenhagen 🇩🇰, exploring cutting-edge research on trustworthy machine learning. Join us at SaTML 2025, the premier conference on AI security, AI privacy, and AI fairness! 👉 satml.org/attend @satml.org
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), April 9-11, 2025, Copenhagen.
074
Konrad Rieck 🌈 @rieck.mlsec.org · 13/12/2024
This work is an unusual collaboration of folks from adversarial learning and hardware security. It took some effort to design a dormant backdoor small enough to fit into an FPGA accelerator. In the end, just 30 parameter changes—0.069% of the model—were enough for success. 2/3
Left: Box-plot of the parameter distribution in the final layer before and after backdoor insertion. Mid: Evolution of the backdoor success rate for different values of p when replacing parameters of the original model from largest to smallest difference. Right: Evolution of the backdoor success rate for p= 1 and different regularization strengths λ.
100
Konrad Rieck 🌈 @rieck.mlsec.org · 13/12/2024
Is your GPU trustworthy? 🤔 Today, Julian presents our work on implanting machine learning backdoors in hardware at @acsacconf.bsky.social. Our backdoors reside within a hardware ML accelerator, manipulating models on-the-fly and invisible from outside. mlsec.org/docs/2024-ac... 1/3
Overview of our hardware-based backdoor attack.
1126
Konrad Rieck 🌈 @rieck.mlsec.org · 27/11/2024
No plans for April 9–11 yet? Why not spend a fantastic week in beautiful Copenhagen, exploring top research on trustworthy machine learning? Registration for IEEE SaTML is now open: satml.org We are also offering travel scholarships: satml.org/scholarships/
060
Konrad Rieck 🌈 @rieck.mlsec.org · 08/11/2024
🚨We’re thrilled to announce the keynote speakers for Michael Veale (@michae.lv), Kamalika Chaudhuri (UCSD), and Matt Turek (DARPA). 👉 satml.org/keynotes/ Don’t miss out on #SaTML2025 in Copenhagen🇩🇰, April 2025!
Michael VealeKamalika ChaudhuriMatt Turek
061
Konrad Rieck 🌈 @rieck.mlsec.org · 05/09/2024
Got some hot research cooking? 🔥 Two weeks until the SATML paper deadline! We’re eager to see your work on secure, private, and fair machine learning, as well as any other aspects of machine learning system security. 👉 satml.org/participate-... ⏰ Deadline: Sep 18
000
Konrad Rieck 🌈 @rieck.mlsec.org · 04/09/2024
We’re excited to announce this year’s competitions for SATML 2025! 🎉 Get ready for four fun challenges tackling prompt injection, data leakage, membership inference, and malware detection. You can find all competitions and their websites here: satml.org/competitions/
000
Konrad Rieck 🌈 @rieck.mlsec.org · 05/08/2024
Mark you calendars. We’re thrilled to announce the Call for Papers for the 3rd IEEE Conference on Secure and Trustworthy Machine Learning. We seek papers on secure, private, and fair machine learning algorithms and systems. 👉 satml.org/participate-... ⏰ Deadline: Sep 18
Call for Papers: SaTML. Deadline: September 18, 2024
020