1
We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them
BinaryAudit benchmarks AI agents using Ghidra to find backdoors in compiled binaries of real open-source servers, proxies, and network infrastructure.
Connect Claude Code, Codex and Cursor session costs to engineering work and outcomes. Find wasted tokens, repeated failures and practices worth sharing.
Visit quesma.com → RSS feedOn Hacker News Sep 2025 – Oct 2026
AI & Machine Learning 10Tools & Productivity 4Security & Privacy 2Software Engineering 1Life, Learning & Writing 1Infrastructure & DevOps 1
BinaryAudit benchmarks AI agents using Ghidra to find backdoors in compiled binaries of real open-source servers, proxies, and network infrastructure.
Local LLMs prioritize privacy over security. Our research reveals a 95% backdoor injection success rate.