Cryptographer Matthew Green: AI worms that pick targets and self-modify are a real threat
matthew_d_green · x · 2026-10-14
Cryptographer Matthew Green pushes back on infosec figures dismissing AI security risks. Unlike traditional worms, AI-enabled ones can intelligently choose targets and self-modify. He argues that without AI, the community would be eager to glue together a self-replicating worm from tools that find 0days and autonomously scan networks—so dismissiveness is cope, not analysis.
Related event: Cryptographer Matthew Green Maps Out the AI Agent Worm Threat(8 posts)→
More from Safety
- PS5 hypervisor defeated as jailbreak crosses a critical threshold — lxfater · 2026-10-14
- Filename-only guard in VS Copilot led to high-severity RCE, patched this Patch Tuesday — wunderwuzzi23 · 2026-10-14
- Security researcher: LLMs will take over threat detection, bitter-lesson style — HankYeomans · 2026-10-14
- Claude refuses to bypass robots.txt, sparking worries about AI over-compliance — RexDouglass · 2026-10-14
- An OpenAI Employee Allegedly Used a Chatbot to Help Plant a Recording Device at the Office — Wired AI · 2026-10-14
- OpenAI in Talks to Buy Security Firm Trail of Bits to Boost Cybersecurity Business — matthew_d_green · 2026-10-14