Stolen Thoughts
Encrypted chain-of-thought blocks returned by Anthropic, OpenAI and Google APIs are interchangeable across sessions, users and models. We exploit this to decode hidden reasoning at scale.
Stealing Reasoning Traces from Proprietary LLM APIs Alexander Panfilov1 2 3 4* David Schmotz2 3 4* Ilia Shumailov5* Luca Beurer-Kellner6 Joachim Schaeffer1 Ameya Prabhu2 4 7‡ Jonas Geiping2 3 4‡ Maksym Andriushchenko2 3 4‡ 1MATS Research 2ELLIS Institute Tübingen 3Max Planck Institute for Intelligent Systems 4Tübingen AI Center 5AI Sequrity Company 6Snyk 7University of Tübingen *Equal contribution, order decided by dice roll · ‡Equal supervision TL;DR Proprietary reasoning can be recovered from its encrypted traces. Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks…
saved by
related reading
- Stealing Reasoning Traces from Proprietary LLM APIsresearch.snyk.io
- Why Frontier AI Labs Fight to Hide Chain of Thought — Ilia Shumailov & Alexander Panfilovyoutube.com
- [2608.09867] Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
- Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
- Let’s talk about encrypted reasoningblog.cryptographyengineering.com
- [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
- [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org
- [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
- [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
- How AI Is Learning to Think in Secretnickandresen.substack.com
- Do reasoning models use their scratchpad like we do? Evidence from distilling paraphrasesalignment.anthropic.com
- [2510.09714] All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Languagearxiv.org