Researcher Uses GPT-5.6 to Break Block Cipher MERIDIAN
evilsocket · x · 2026-08-26
Security researcher JP Aumasson demonstrated using OpenAI's GPT-5.6 Sol to break the block cipher MERIDIAN posted on ePrint. GPT identified a critical flaw within 5 minutes: the cipher is not a permutation, meaning distinct plaintexts can map to the same ciphertext, making unique decryption impossible. It also found a differential exceeding the claimed bounds. This challenges the author's previous belief that LLMs couldn't break symmetric crypto.
More from Safety
- PACT AI launches to bridge the gap in AI system verification — Miles_Brundage · 2026-08-27
- SecOPD Mitigates Adaptive Prompt Injection via On-Policy Distillation — Yibo Peng · 2026-08-27
- Inside the Anthropic Author Settlement: A Novelist's Perspective — rvp · 2026-08-27
- Long Read: AI Is Buying the Data of Dead Companies — rvp · 2026-08-27
- Robin Hanson: AI Claims of Danger vs Actual Harms — amcafee · 2026-08-27
- Age verification laws are building the internet's next identity layer for AI agents — provenauthority · 2026-08-26