Standard binary hardening cuts Codex's 20 AI exploits down to just 2
dawnsongtweets · x · 2026-11-12
From the CyberBinGym thread: rebuilding the 20 targets Codex successfully exploited with standard binary hardening (stack canaries, PIE, full RELRO, NX, Fortify) drops successful exploits from 20 to 2 (10%). Codex still recovered the vulnerability on 15 of the 20 hardened targets but couldn't complete exploitation.
Takeaway: classic layered defenses remain highly effective against AI-generated exploits, though they don't close every path — hardening is still the most practical mitigation today.
More from Safety
- Andrew Critch: stop calling extinction risks "improvement"—RSM vs RSI matters — AndrewCritchPhD · 2026-11-12
- Any US State Could Legalize AI Safety Coordination via Parker Immunity — TinfoilTricorn · 2026-11-12
- Chicago schools block ChatGPT and Gemini as an AI song nears top of Korean charts — lmoroney · 2026-11-12
- AI Horizons Forum to gather ~1,000 AI safety leaders in SF, December 12–13 — austinc3301 · 2026-11-12
- Probes already deployed as first stage of OpenAI monitoring, discussant says — dfrsrchtwts · 2026-11-12
- Kaspersky details Black Owl APT breach of software vendor eyeing supply-chain attack — cyb3rops · 2026-11-12