Anthropic's Claude Mythos Finds Encryption Flaw Following OpenAI Agents' Containment Breach

Fonte: International Business Times

United Arab Emirates' Minister of State for Artificial Intelligence Omar Al Olama speaks during the UK Artificial Intelligence (AI) Safety Summit at Bletchley Park, in central England, on November 1, 2023. Leon Neal/AFP KEY POINTSClaude Mythos Preview autonomously discovered mathematical flaws in a weakened version of the Advanced Encryption Standard (AES), engineering an attack 200 to 1,000 times faster than previous human research. Separately, Claude Mythos Preview identified a vulnerability in HAWK, a digital signature scheme under consideration by the National Institute of Standards and Technology (NIST) as a post-quantum encryption standard.