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
- Comprehension Audits: New Paper Proposes a Gate for AI-Written Code at Frontier Labs — ronbodkin · 2026-10-16
- Developer trains his own PII detector, dissatisfied with existing solutions — HankYeomans · 2026-10-16
- Experts Across Fields Estimate 1-16% AI Catastrophe Risk by 2100, Survey Shows — ben_j_todd · 2026-10-16
- Untethered iOS 27.0.1 jailbreak demoed on iPhone 18 Pro at Hexacon — jedisct1 · 2026-10-16
- China requires MOFCOM approval to open-source models above 2T params or 10^26 FLOPS — zephyr_z9 · 2026-10-16
- Universal forgery attack breaks Chinese PQC signature Origami using only the public key — matthew_d_green · 2026-10-16