Discovering cryptographic weaknesses with Claude \ Anthropic

Anthropic researchers find weaknesses in cryptographic algorithms with Claude Mythos Preview

Frontier Red Team Discovering cryptographic weaknesses with Claude Jul 28, 2026 Summary Using Claude Mythos Preview, researchers at Anthropic have discovered improved ways to attack cryptographic algorithms (the mathematical methods used to keep online data private). The first attack significantly weakens HAWK, a digital signature scheme that was built for a post-quantum world. The second identifies a new way to attack round-reduced AES, the most widely used symmetric cipher. These are substantial research advances, but they do not currently affect any production systems. This post describes b

saved by

• Shubham Shah
• Emma Guo
• Uzay Girit
• Jaeho Lee
• Carmen Gutierrez
• jenny peng

related reading

• Assessing Claude Mythos Preview’s cybersecurity capabilities \ Anthropicred.anthropic.com
• Some thoughts about Anthropic’s new cryptanalysis resultsblog.cryptographyengineering.com
• Project Glasswing: Securing critical software for the AI era \ Anthropicanthropic.com
• Investigating three real-world incidents in our cybersecurity evaluations \ Anthropicanthropic.com
• Claude Mythos Preview System Cardwww-cdn.anthropic.com
• Countering misuse of AI: September 2026 / Anthropicanthropic.com
• An alignment assessment of recent cybersecurity incidentsanthropic.com
• Measuring LLMs’ ability to develop exploits \ Anthropicred.anthropic.com
• Is Mythos good at cyber because it kept hacking Anthropic's sandboxes during training? — LessWronglesswrong.com
• Claude Mythos Preview System Cardwww-cdn.anthropic.com
• Disrupting the first reported AI-orchestrated cyber espionage campaign \ Anthropicanthropic.com
• Cybersecurity Looks Like Proof of Work Nowdbreunig.com