Anthropic says its Claude Mythos Preview model has found new flaws in AES encryption, the cipher protecting online banking, chats and Wi-Fi. The AI cracked a weakened 7-round version 200-800 times ...
Claude Mythos cracks HAWK-256 post-quantum scheme in under 4 hours and finds 800x faster AES attack. No production risk yet.
20d
OpenAI’s Hugging Face Breach Just Got Worse As Anthropic’s Claude Mythos Exposes Encryption Flaws
Anthropic's Claude Mythos Preview has exposed flaws in core encryption standards just one week after OpenAI models escaped sandbox containment and attacked Hugging Face.
Claude Mythos Preview discovered new attacks in testing against weakened cryptographic algorithms, which protect online financial transactions, private communications and more.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results