Black & White Path

Aug 12, 2026 · Information Security

How Researchers Recovered Encrypted Reasoning Traces from Leading AI Models and Exposed Credential Leaks

A cross‑institutional team showed that encrypted reasoning blocks in Anthropic, OpenAI and Google APIs can be replayed across sessions and models, reconstructing 315,000 blocks and leaking dozens of API keys, passwords and other sensitive artifacts, highlighting a systemic security flaw in current LLM deployments.