Wrote some slides on symbolic exploit search / synthesis... kmicinski.com/ai-security-co…

DecBench is growing fast, but I want to remind people that I manually verify results and submissions on the site. That means two things: 1) if you see results elsewhere and not on DecBench.com, I can't speak to their quality. 2) Result updates can be slower, so please don't spam 👍

I am recruiting a postdoc to work with me here in Paris on fuzzing and backdoor detection! ➡️ Do not hesitate to apply or share the offer!

I'm pleased to announce a new release of the #idalib #Rust bindings for @HexRaysSA IDA Pro! This release provides new APIs and bug fixes. Thanks to new and existing contributors @mcbbugu, Amaan Qureshi, and @0xdea for their work on this release. github.com/idalib-rs/idalib.…

A new decompiler approach enters the ring!

Super interesting work, and improving on structure recovery is really impressive; that's a seriously hard problem that has had a lot of previous work

it's great that with decbench, we have a high-quality public benchmark. yet, decompiler evaluation remains hard, and I see two primary challenges right now: 1. high-quality, real-world-like, fully private data. Frontier LLMs have seen virtually every open source function in existence and leakage is not fully avoidable, something we also cannot rule out for our model. 2. finding a better proxy for semantic fidelity. A program can recompile, but do something entirely different. A program can also recompile, have a totally different byte-level structure from the groundtruth, and still do the same job. Dynamic-execution based attestation is tough to get correct at scale, but might be a better signal in the long run.

we submitted and verified our results via the public site: decbench.com/leaderboard/?da… (`normalize` as there is no arch-specific view right now) it's cool to see that our {static context collection -> one-shot decompilation} approach can compete with fully agentic frontier LLMs

today, we @RevEng_AI released the next generation of our decompiler: Ventris the new model comes with improved struct layout recovery, better PE support, and more. on decbench, we beat all other available decompilers in structure recovery, and achieve #2 rank overall

I've shared the list of malicious models detected by MLTracer, along with a systematic analysis of techniques for evading existing model scanners, in the following GitHub repo. github.com/binarly-io/ai-sup… In short, the AI supply chain security field still likely has a lot of room for improvement.

"Software protection is futile, AI will break it", they said. But, does it? how? To shine some light read about Rémy Salim's experiments in "Defeating AI-Assisted Reverse Engineering" Where is the fair play, Claude? blog.quarkslab.com/defeating…

Schrödinger’s TOCTOU — a bug class where a struct’s size mod 16 decides if you’re exploitable, where -O2 saves you and -O3 kills you, where a compiler upgrade introduces the bug, and a downgrade… introduces it too. Invisible, intractable, everywhere. github.com/xoreaxeaxeax/schr…

Static Devirtualization of Tencent VM. There are many others with similar results to ours, we have had the VM devirtualized for several months now. Others are posting full devirt bins, so we feel it is ok to release our research now. back.engineering/blog/31/07/…

I'm pleased to announce a new release of the #idalib #Rust bindings for @HexRaysSA IDA Pro! This release adds compatibility with latest SDK (v9.4), and a couple of bug fixes. Thanks to @0xdea and @yeggorv for their contributions. github.com/idalib-rs/idalib.…

We are approaching perfect binary decompilation, and, crazier still, LLMs may soon be the best decompilers on the planet. I'd like to introduce DecBench, an evaluation site to determine how close we are to completing the field of perfect decompilation. Links and more in 🧵

Really exciting to see the latest research from the RevEng.AI team tackling one of cybersecurity's biggest challenges: detecting malicious code at scale. As attackers continue to evolve, signature-based approaches alone are no longer enough. This research highlights how AI can identify malicious behaviour in compiled binaries by understanding the underlying semantics of machine code, enabling the detection of previously unseen malware variants without relying on constant rule updates. reveng.ai/blog/detecting-mal…

📢 IDA 9.4 is here! Huge thanks to our beta testers for spending the last several weeks refining this release. • The Apple Dyld Shared Cache workflow has been rebuilt from the ground up. • The decompiler now speaks Swift, with proper ABI modelling for self, async context, and error paths. • Two new processor modules land — Qualcomm Hexagon and MCore. • Navigation gets a major upgrade with Pathfinder and a redesigned Jump Anywhere. • The Teams add-on now runs on Git. • And idalib, previously Pro-only, now ships with IDA Home. 👉 Read the blog for the full breakdown and/or jump ahead to the release notes, then grab your update in the Download Center. hex-rays.com/blog/ida-9.4-re…

interesting new paper on LLM-based decompilation: AutoDecompiler is an RL-optimized model for feedback-driven, multi-turn decompilation. although previous one-shot approaches might have optimized for recompilation or even executability, they did not utilize feedback directly.

today I had the pleasure of presenting our work on high-throughput type recovery for binaries at ACM CODASPY! lots of great presentations and discussions all around. slides: github.com/pr0me/xtride/blob… paper: arxiv.org/pdf/2603.08225

(for Rust people) Finally got around to writing about Diplomat, the FFI tool I've been building and using for the last five years. Check it out! manishearth.github.io/blog/2…