On Thursday afternoon, I am thrilled to give my first r2ai & ghidraMCP workshop at BruCON. Pre-requisites: you are good to go if you already have reversed a binary (with whatever #disassembler, it doesn't matter) OR if you have basic skills and understanding in #assembly. #mcp #LLM #AI

Slides of my prez at Barb'hack: www.fortiguard.com/events/6189/... Understand what a recent sample of Linux/Trigona #ransomware does. Learn how to spot #AI errors (hallucinations, omissions etc), learn how to tweak context length, output token limits to get the best out of your model. #barbhack25

I had (several) interesting questions yesterday on r2ai. One of them was that, obviously the tool needed to be used by an experienced reverse engineer. I'd like to comment a bit further. I feel normal that such a tool cannot be used by total beginners. All jobs require some adequate training. 1/n

Barb'hack is over and it was a pleasure to attend: very nice folks, friendly organizers, excellent food, best rumps lol and a CTF with a videogame interface+ challenges on Minitel. I loved it! Kudos to the staff. #barbhack25

I've very happy to speak at Barb'hack on Saturday. barbhack.fr/2025/fr/conf... There will be 2 demos. One live. One recorded - simply because I don't have the guts to do it live ;P We reverse engineer Linux/Trigona and Linux/Shellcode with radare2 + AI + HI HI standards for Human Intelligence ;P

Overlays are often used in Android malware. They are actually a burden to other domains such as browser extensions. This research, by Marek Toth, shows how click jacking [on hidden overlays] can trick the end-user in sharing his/her entire password manager. marektoth.com/blog/dom-bas...

Last chance to share your research at VB2025. Whether you have fresh research, practical insights, or real-world case studies to share, now is your moment to step into the spotlight! 📅 24 Aug 2025 — only 5 days left 📍 Berlin. 24–26 Sept 2025 👉 tinyurl.com/3mccm8br

I've recently setup a LM Studio server, with several models including gpt-oss. I can use it from my disassembler, here to analyze a Linux/Trigona sample. Learn more about Trigona at Barb'hack on Aug 30 in Toulon. #AI #malware #reverse #assembly #context #lmstudio #GPT

I love this kind of analysis 😍 Well done! Exploiting the Thermomix. Hey @synacktiv.com can you cook me a chocolate cake? ;-) www.synacktiv.com/en/publicati...

My blog post on how AI is reshaping malware and malware analysis is out: www.fortinet.com/blog/threat-... Examples on Linux/Trigona, Linux/Prometei, Linux/Ladvix and Android/SpyLoan. Enjoy. #malware #r2ai #r2 #claude #delphi #trigona #rust #flutter

W32/SkyAI uses AI? So do I. cryptax.medium.com/w32-skyai-us... - Where the malware loads the AI prompt, what for, why it fails. - How to find the encryption key with AI - Extract & decrypt the embedded PE - How the malware checks if it's on a VM - R2ai tips when curl argument is too long

Le nouveau zine de @b0rk.jvns.ca : Les règles secrètes du terminal 👉 jvns.ca/blog/2025/06...

Vous connaissez les vidéos de @tixlegeek.bsky.social ? Avec cet adorable Tux animé ? Ben, ça me faisait trop envie. Alors j'ai fait pareil avec Pico le Croco ! J'ai repris les explications de @tixlegeek.bsky.social dans le Twitch @laluka.bsky.social EP 193, et j'ai codé pour Pico :)

Nicolas Rouvière, of Ph0wn and SHL, will show you how to use Qiling in practice, for dynamic binary emulation. Don't miss it: on-site at SHL (Vallauris), June 19 at 7pm. In 2024, Nicolas used Qiling to solve the Ph0wn CTF teaser. See how here: github.com/ph0wn/writeu... #qiling #CTF #binary

Hey, I'd like to share the best talks/papers/videos/tools/CTF challenges I encountered in 2025 H1. This is the official "Cryptax Award 2025 H1" (lol). Congrats! cryptax.github.io/nomination-2... cc: @elbsides.bsky.social @northsec.io @radareorg.bsky.social @bsideskrs.bsky.social

How many times will I have to say this? Antivirus is not stupid and does NOT rely on fixed hashes or whatever to detect malware. This is an outdated myth from prehistoric times. Malware "signatures" understand binary formats + assembly and can easily dynamically detect variants.

Keynotes are a difficult exercises (for me). I'll be closing the @elbsides.bsky.social conference tomorrow with a *Quizz* keynote on how AI is used by malware authors (attack) and malware analysts (defense). I even hope to have time for a short demo :) #AI #malware #keynote #elbsides

📣 📣 Elbsides 2025 conference is fully booked 📣 📣 Really looking forward to seeing a full conference room on Friday and listening to our wonderful speakers presenting their latest insights. #Elbsides2025 #Infosec #Cybersecurity #Hamburg

MCP should ask for user approval for each of its steps. And I mean not just high level questions "are you ok that I rename this file?" but we need to see exactly what is going to run on our host: e.g. "mv file1 file2", and only that can get executed. 1/2

Interesting read: invariantlabs.ai/blog/mcp-git... It shows how GitHub MCP can be exploited to leak private information. You create a dummy issue with a prompt that asks to leak the information, and there it goes.

📣 📝 We are proud to announce the #r2con2025 call for papers! Expect it online and around Nov/Dec! Submit your talk proposals and stay tuned for updates! 👉 radare.org/con/2025

Can't wait until next Friday for Elbsides 2025 to happen. Don't miss this opportunity to get inspired, informed and connect. We are nearly sold out - register now to be part of the #ITSecurity community in #Hamburg on June13th. www.elbsides.eu/2025/registr... #Elbsides2025 #Infosec #Cybersecurity

Cette semaine à #SSTIC2025, j’ai co-présenté notre talk la prise de contrôle à distance d’un système d’infodivertissement via Bluetooth 🚗📡 Slides & vidéo : www.sstic.org/2025/present...

Just captured all flags of the Badge CTF at @bsideskrs.bsky.social :) A fun badge based on RP2040 :)

@uybhys.bsky.social j'ai eu peur unlockyourbrain.bzh/cfp/ : "Vous pouvez proposer des interventions jusqu’au 1er juin 2025 00:00 (Europe/Paris) !" mais heureusement ça semble être "You can enter proposals until 2025-06-30 00:00"

Slides of my presentation at @northsec.io are available here www.fortiguard.com/events/6101/... Work on 2 different malware samples and showed how good the AI performed overall in decompiling them or de-obfuscating, but also some errors that it did in details. #r2ai #ladvix #shellcode #linux #IoT

Today I presented at #hackbcn some practical usecases integrating language models for reverse engineering purposes with #radare2 Check out my slides at radare.org/get/r2ai-hac...

Today I wrote an #r2ai widget for iaito, the official #radare2 frontend.

📅 Mark your calendars! www.hexacon.fr

WhatsApp has a new feature called “advanced privacy mode” that limits the types of “sharing” chat participants can do. My understanding is that this will help protect chats against possible risks from future AI assistance features. blog.whatsapp.com/introducing-...

New from 404 Media: hackers are injecting mass shooting videos into random Starcraft 2 matches. The Starcraft community is awash with people saying random videos have appeared in game, including those designed to trigger seizures. Blizzard hasn't responded www.404media.co/hackers-are-...

Vous voulez acquérir un prototype du #CoolKidsBadge 2025 et aider au développement du produit final? Rendez vous sur le stream de ce soir à partir de 21h30! twitch.tv/tixlegeek

Interesting read on prompt injection security risks for MCP servers simonwillison.net/2025/Apr/9/m... #AI #MCP #security

Wrote a paper, with Daniel Nakov, on comparing the #quality & the speed of #malware analysis assisted by #r2ai, or without. Spoiler 1: quality is =, speed is ++. Spoiler 2: do not expect to get good results in a single question. arxiv.org/pdf/2504.07574 cc: @radareorg.bsky.social #arxiv #radare2

Je ne l'avais pas vu passer ce CFP, et justement, je cherchais les dates de la conférence en 2025, donc on dirait 7 et 8 novembre 2025 :)

Hey, can someone please endorse me for arxiv computer science? I want to publish on malware analysis & radare2 & r2ai, and I haven't used arxiv before, so I need an endorsement from someone who's already published on ArXiv Computer Science cat. This is the link, thanks: arxiv.org/auth/endorse...

Wrote “Analyzing a shellcode with #r2ai" article posted in the latest PagedOut ezine pagedout.institute/download/Pag... Enjoy! #shell #linux #radare2 #AI #malware

Yop ! 🚫🐟️ Vous avez kiffé le premier Stream AI sur R2-AI, DECAI, & FABRIC avec Victor Louis Poucheret / @DoomerOutrun (X) & Axelle Apvrille / @cryptax.bsky.social ? Dope. 😎 youtube.com/live/95WSov_...

Today, @volexity.com released GoResolver, open-source tooling to assist reverse engineers with obfuscated Golang samples. @r00tbsd.bsky.social & Killian Raimbaud presented details at INCYBER Forum earlier today. Learn how GoResolver works+where to download it: www.volexity.com/blog/2025/04... #dfir

Side by side decompilation of the main entry point of the unpacked DEX of Android/Crocodilus. On the left, decompiled using Mistral (and r2ai). On the right, decompiled with JEB Decompiler. Both are excellent :) #radare2 #AI #mistral #JEB #crocodile #malware #Android

Certains avaient un peu du mal à flagger à ph0wn CTF. Nous avons décidé de les aider. Suivez bien la vidéo. asciinema.org/a/710926 #ph0wn #CTF #flag

Demain, ph0wn labs #2 au SHL (shl.contact). Venez faire une farce sur le badge de Pico. #pico #raspberry #badge #ph0wn #SHL #CTF #reverse

Le CFP de Pass The Salt se termine dimanche. cfp.pass-the-salt.org/pts2025/cfp

We've had AI-tools in r2 for months (year?), and now people are adding tools to Ghidra with MCP :) See this video of @lauriewired.bsky.social www.youtube.com/watch?v=u2vQ.... Yet, you get better results with r2ai now because it improves code "globally" too. Ex: www.fortinet.com/blog/threat-...

Looking forward to discuss DeepFake risks in Fribourg Tomorrow. Join if you are nearby! #cyberSecurity www.fr-cybersecurity.ch

Hello ! ⚔️ On se retrouve ce (Mardi 25) soir à 21h Stream PURE AI, avec en particulier une présentation de fabric par @DoomerOutrun (X) / Victor Louis Poucheret et r2ai par @cryptax.bsky.social / Axelle Apvrille ! 🥰 See you there ! www.twitch.tv/thelaluka

Spring is here and you are all inspired to write a paper for @elbsides.bsky.social , right?? RIGHT!!! Just grab your computer - or pen and paper - and jot down the ideas that you would like to share with our audience in Hamburg this summer. (CFP open until April 11th). www.elbsides.eu/2025/cfp/

Slides of my talk "Malware analysis with R2AI" @1ns0mn1h4ck.bsky.social filestore.fortinet.com/fortiguard/r... Demo of string obfuscation on Linux/RudeDevil: asciinema.org/a/708621 Download and contribute to r2ai: github.com/radareorg/r2ai @radareorg.bsky.social #AI #radare2 #malware #linux

🚨𝗬𝘂𝘁𝗮𝗻𝗶𝗟𝗼𝗼𝗽: 𝗔𝗜-𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗺𝗲𝘁𝗮𝗺𝗼𝗿𝗽𝗵𝗶𝗰 𝗮𝗴𝗲𝗻𝘁🚨 Demoed at #InsomniHack 🔹 Fileless, self-learning, re-obfuscating, autonomous with reasoning 👉🏻AI does help malware, but still needs guidance 👉🏻Behavior-based detection still can win 👉🏻Not the end of cybersecurity - yet #AI @orangecyberdefense.bsky.social

The CTF is over! 🎉 Huge congrats to our podium finishers: 🥇 PokémonCollection, 🥈 FlatNetworkSociety, and 🥉 polyflag! 🏆👏 Big thanks to all participants you crushed it! 💪 See you next year for more hacking madness. Thanks for being part of Insomni'hack 2025! #INSO25 #CTF