EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models
Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs can be directly extracted from black-box models remains largely unexplored. In this work, we systematically study whether hidden CoTs can be extracted near-verbatim from black-box LRMs through API interactions. We identify a previously overlooked reasoning replay surface between tool calls and develop EchoCoT, a multi-step attack that iteratively extracts hidden CoTs using API-returned fidelity signals. We further develop an LLM-based optimization framework that automatically searches for an effective universal injection trajectory across various datasets. We evaluate EchoCoT on three open-source and five frontier proprietary LRMs. On open-source LRMs, EchoCoT achieves up to 66.4\% near-verbatim extraction success, with the extracted trace length within 10\% of the target and at least 90\% of tokens exactly matching the target CoT. The same injection trajectory also generalizes to unseen datasets, achieving up to 80\% extraction success under the same criterion. For tested frontier proprietary LRMs, a substantial fraction of extracted CoTs closely align with provider-reported reasoning lengths and available CoT summaries. EchoCoT can also extract very long CoTs: on Gemini-2.5, it extracts 33,463 tokens from a 32,948-token target. These results establish hidden-CoT extraction as a practical security risk and highlight the need to better protect hidden CoT assets.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering
In today's fast-paced industry, professionals face the challenge of summarizing a large number of documents and extracting vital information from them on a daily basis. These metrics are frequently hidden away in tables …
Few-Shot LearningQuestion AnsweringRAGRetrieval-augmented GenerationImplicit Chain of Thought Reasoning via Knowledge Distillation
To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural langu…
Knowledge DistillationMathUnderstanding Hidden Computations in Chain-of-Thought Reasoning
Chain-of-Thought (CoT) prompting has significantly enhanced the reasoning abilities of large language models. However, recent studies have shown that models can still perform complex reasoning tasks even when the CoT is …
Language ModelingLanguage ModellingLet's Think Dot by Dot: Hidden Computation in Transformer Language Models
Chain-of-thought responses from language models improve performance across most benchmarks. However, it remains unclear to what extent these performance gains can be attributed to human-like task decomposition or simply …
EchoCoTr: Estimation of the Left Ventricular Ejection Fraction from Spatiotemporal Echocardiography
Learning spatiotemporal features is an important task for efficient video understanding especially in medical images such as echocardiograms. Convolutional neural networks (CNNs) and more recent vision transformers (ViTs…
Video Understanding