All posts
Topic
Infosec
4 articles on infosec.
The AI Reverse-Engineering Studio: 20 Open-Source Tools Around REA, Explained
A viral post bundles 20 open-source repos into an "AI reverse-engineering studio" built around REA. What each tool actually does (Ghidra, GhidraMCP, ida-pro-mcp, jadx, Apktool, Frida, ILSpy, radare2, rizin, x64dbg, ImHex, angr, mitmproxy, dnSpyEx, RAD Debugger), how they chain together, which claims we could not verify, and how defenders should use and defend against it.
October 27, 2026
AI Clean-Room Rebuilds: The SPEC.md → Oracle Loop, and Where the Law Draws the Line
AI agents can now study a binary, write a behavioural SPEC.md, rebuild the software from the spec, and check it against the original as an oracle until it matches. How the clean-room loop works, why the "clean-room wall" matters, what US and EU law actually allow (Sega v. Accolade, Sony v. Connectix, Bowers v. Baystate, DMCA 1201(f), EU Directive 2009/24/EC), and what it means for defenders.
October 27, 2026
Google Mantis: An Open-Source Toolkit for AI Agents That Find, Reproduce, and Patch Bugs
Google quietly open-sourced Mantis (Apache-2.0) in September 2026 — a modular, stack-agnostic toolkit that lets an AI coding agent autonomously find, reproduce in a sandbox, and patch vulnerabilities, verifying each fix with an adversarial loop. What it is, how the pipeline works, how to run it, and the caveats that matter.
October 27, 2026
Autonomous AI Vulnerability Patching Tools Compared (2026): Mantis vs CodeMender vs Aardvark vs XBOW vs AIxCC
A sourced comparison of the autonomous AI tools that find and/or patch vulnerabilities in 2026 — Google Mantis, OpenAI Aardvark, XBOW, the DARPA AIxCC cyber reasoning systems, GitHub Copilot Autofix, Semgrep Assistant, Mobb, Pixee, Corgea, OSS-Fuzz-Gen — plus Google DeepMind CodeMender: what each does, which is better for what, and how Google's two efforts differ.
October 27, 2026