Researchers found every major AI provider encrypts reasoning tokens with a single global key—and exploited it to decode a trove of data.

Microsoft Threat Intelligence examines DeadLock ransomware, an emerging financially motivated operation distinguished by its ...

Researchers devised a way to extract “reasoning traces” from Claude, GPT, and Gemini. What they found, they say, indicates ...

A team of eight researchers reports that encrypted reasoning blocks returned by major AI model APIs can sometimes be recovered.