Researchers Find Easy Way to Extract Encrypted Chain-of-Thought from OpenAI and Anthropic

Researchers have discovered a method to extract encrypted chain-of-thought reasoning from the APIs of Anthropic, OpenAI, and Google. By exploiting a vulnerability where encrypted reasoning blocks can flow across sessions and models, attackers can have weaker models decode and output hidden reasoning from flagship models. The study was released on August 10 by MATS Research, the University of Tübingen, and the Max Planck Institute for Intelligent Systems.