Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Novel research on extracting reasoning traces from LLM APIs, highly strategic for AI security auditing.
Researchers from ELLIS Institute Tübingen, Max Planck Institute, and Snyk demonstrated that encrypted reasoning blocks returned by Anthropic, OpenAI, and Google LLM APIs are portable across sessions, users, and models, enabling extraction of hidden chain-of-thought in two API calls. By replaying a block from claude-opus-4-8 into claude-haiku-4-5 with a prompt to transcribe, they recovered full reasoning verbatim, verified against 120 Codeforces problems up to 12,000 tokens. The architectural vulnerability stems from providers returning encrypted blocks to clients rather than storing them server-side, making session logs, agent traces, and tool-call history a decryption surface.