CryptanalysisBench

Anthropic's LLM Claude Mythos discovered cryptanalytic attacks on the post-quantum signature scheme HAWK and reduced-round AES-128, but the attacks are not practical and pose no threat to full AES. Th…

Anthropic researchers used Claude Mythos Preview to discover new weaknesses in two cryptographic methods, including HAWK, a digital signature scheme under NIST review for post-quantum security, and a …

A new benchmark, CryptanalysisBench, shows that five frontier large language models can break 65%-86% of Tier 1 cryptographic schemes and produce novel cryptanalysis, including a key-recovery attack o…