What a great honor and recognition to receive the @IEEESSP Test of Time Award for our work on code property graphs. Thank you all so much! 🙌📜 @bifoldberlin @TUBerlin. A quick throwback to our paper's journey . 1/6.

RT @RhysSullivan: these gpt-5 numbers are insane 🤯

Join millions who have switched to Grok.

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

RT @random_walker: Some aspects of AI discourse seem to come from a different planet, oblivious to basic realities on Earth. AI for science….

RT @matthiasboehm7: @mlsec @bifoldberlin @CASA_EXC Thanks for mentioning, it was @SBaunsgaard's contributions.

This work emerged from a spontaneous collaboration with the group of @matthiasboehm7 at our institute @bifoldberlin and @CASA_EXC . If you'd like to learn more, check out our paper: . Code for crafting your own Chimera examples will follow soon. 4/4.

Fortunately, exploiting these discrepancies is not straightforward, as real-world inputs are typically limited in precision. Still, with some effort, we manage to induce divergent predictions even from 8-bit integers like image pixels, resulting in Chimera images 👾. 3/4.

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

Today, Jonas presents a new type of adversarial examples at @icmlconf! . 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 🤯 . 1/4

RT @arthur_spirling: Deeply concerning to see scholars cut and paste chatGPT suggested citations into their papers without checking whether….

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

RT @mboehme_: Can we statistically estimate how likely an LLM-generated program is correct w/o knowing what is a correct program for that t….

RT @moyix: The code for building and updating the ARVO dataset, a collection of over 5000 memory safety vulnerabilities in open source soft….

RT @jhasomesh: Fantastic venue. Everyone I chatted with was raving about @satml_conf 2025. Plus the current chairs @mlsec and Rachel Cummin….

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

RT @maurapintor: 🚀 Exciting Announcement! 🚀. Get ready for the 18th ACM Workshop on Artificial Intelligence and Security (AISec 2025)!. 📍Co….

RT @mahal0z: I'm proud to announce that myself and @AtipriyaBajaj have created the Workshop on Software Understanding and Reverse Engineeri….

RT @mboehme_: Our paper "Top Score on the Wrong Exam" paper will be presented at #ISSTA25 🐣 in Trondheim!. 📝🧑‍💻http….

RT @niklas2484: Function-level vulnerability detection is dead. Excited to share that our paper "Top Score on the Wrong Exam: On Benchmark….

RT @ELLISforEurope: 📢 ELLIS at ICLR 2025 - We’d like to congratulate the ELLIS community for their impressive contributions to this year’s….

RT @satml_conf: 🚨 SaTML is searching for its 2026 home!.Interested in becoming General Chair and hosting the conference in your city or ins….