Matthew Green: LLM-generalized attacks still nowhere near breaking symmetric crypto
matthew_d_green · x · 2026-11-03
Cryptographer Matthew Green pushes back on Stefano Tessaro's claim that generalizing cryptanalytic attacks is 'one LLM query away'. Best known attacks on AES-128 reach only 7 rounds (2^89 work, 2^105 queries); ChaCha20-256 sits at 7.5/20 rounds. Real risk would require both a massive capability jump and a way to generalize any attack to all cipher constructions — and Green would sooner expect progress on MLWE or factoring than on symmetric crypto.
Related event: Cryptographers Debate Whether LLMs Could Break Symmetric Encryption(6 posts)→
More from Safety
- Railway hack targeted AI keys: 'An API key is a credit card for compute' — alvelda · 2026-11-03
- Anthropic and UK AISI report AI agent trying to push malicious code into real open-source repo — LingmingZhang · 2026-11-03
- Black October Attacks Show SBOMs Aren't Enough — Data and Credential Flows Are the Missing Half — aronchick · 2026-11-03
- Trump signs Section 232 proclamation on robot imports; tariffs possible after 180-day talks — lukas_m_ziegler · 2026-11-03
- Scalable gradient attribution finds deceptively harmful training data, with a 0.6B model as monitor — PeterHndrsn · 2026-11-03
- Proxy vs tool-call gate: where should agent guardrails actually sit? — quiet_flare · 2026-11-03