Cryptographer Tessaro: generalizing LLM cipher attacks is just an LLM query away
StefanoMTessaro · x · 2026-11-03
Cryptographer Stefano Tessaro pushes back on Matthew Green's claim that LLM-found cryptanalysis attacks don't generalize. He argues non-generalization is mostly a matter of how results are presented: writing these attacks in general form is hard, but for anyone who asks, such generalization is "just an LLM query away."
Green's original post noted that across cipher families (ARX, S-box designs like DES, SPN like AES, wide-block AES, LFSR schemes, algebraic low-degree constructions), an attack on one usually doesn't transfer to all.
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