Anthropic's LLM Discovers New Attack Paths for AES and HAWK

matthew_d_green · x · 2026-08-01

Cryptographer JP Aumasson reviewed Anthropic's recent breakthroughs in cryptanalysis using Large Language Models (Claude Mythos).

The author noted that while LLMs cannot currently break symmetric encryption, they show great potential in formalizing attack techniques, verifying complexity estimates, and finding errors in security proofs.

Original post →

More from Research

Research channel →