CryptanalysisBench tests LLMs on 191 real cryptographic schemes
thegautamkamath · x · 2026-07-23
CryptanalysisBench tests whether LLMs can break 191 real cryptographic schemes
The paper introduces CryptanalysisBench, a benchmark at the intersection of AI, math, and cybersecurity.
- It evaluates whether LLMs can perform cryptanalysis on 191 real schemes drawn from past standardization efforts.
- The authors frame cryptanalysis as a key link between AI progress in math and cyber, with direct relevance to digital security.
- The work suggests that LLMs are increasingly capable of assisting with this kind of security analysis.
More from Safety
- AI shrinks the patch window to hours; air-gapped backups are your last line — aakashgupta · 2026-10-26
- NYT roundtable asks five experts what the rules for AI companies should actually be — ShakeelHashim · 2026-10-26
- Google DeepMind pilots world's first double-blind evaluations for frontier models — scychan_brains · 2026-10-26
- LLM back-of-envelope estimate puts PHP vulnerability impact at $1bn–$4bn — S_OhEigeartaigh · 2026-10-26
- US states halt new data centers as 72% of Americans oppose local builds — YvesMulkers · 2026-10-26
- LEMON: zero-shot LLM misbehavior monitor flags hallucinations from attention maps — yoavartzi · 2026-10-26