New Attacks on HAWK and AES Cryptographic Schemes

A frontier lab publishing model-assisted cryptanalysis against HAWK and AES, with the reasoning traces released, is a concrete data point on where AI now sits in offensive-security research.

• chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.

• postAnthropic reports four unintended Claude behaviors on real systems
• postAnthropic launches Cyber Mission with free OSS Scanner
• postClaude Science helps build first full-sky ultraviolet map
• postClaude Optimizes 30+ Open-Source Biology Models to Run 4x Faster

• articleDiscovering Cryptographic Weaknesses with ClaudeAnthropicAI
• articleCryptanalysisBench: Can LLMs do Cryptanalysis?AnthropicAI
• articleStealing Reasoning Traces from Proprietary LLM APIssimonwillison.net

Checking sign-in…

Loading comments…