1
LLM Model-Swapping Trick Can Expose AI Reasoning Traces
模型替换攻击可撬开AI思维链，警惕推理过程泄露风险
Article URL: https://ai-updates.net/model-swapping-exposes-ai-reasoning-traces/ Comments URL: https://news.ycombinator.com/item?id=49265641 Points: 2 …
2
Stealing Reasoning Traces from Proprietary LLM APIs
一条加密token泄露链，暴露闭源大模型推理过程可被逆向窃取，安全边界再受拷问。
Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name ( stolen-thoughts.com ) for a neat paper : Anthropic, OpenAI, and Google retu…
3
Stealing Reasoning Traces from Proprietary LLM APIs
揭秘如何从专有大模型API中窃取隐藏推理过程，安全研究者必读。
Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name ( stolen-thoughts.com ) for a neat paper : Anthropic, OpenAI, and Google retu…
4
Stealing Reasoning Traces from Proprietary LLM APIs
揭秘API加密推理痕迹的可窃取性，安全研究必读。
arXiv:2608.09867v1 Announce Type: cross Abstract: Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of…
5
Constraint-Anchored Reasoning Traces
15页论文提出约束锚定推理痕迹方法，为AI推理提供新视角，ACM MM 2026收录。
arXiv:2607.16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorr…
6
ReasonOps: Operator Segmentation for LLM Reasoning Traces
新方法将LLM推理轨迹分割为操作符，提升可解释性与效率
arXiv:2605.29192v1 Announce Type: new Abstract: Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack …
7
Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
从LLM推理中提取搜索树，揭示其规划过程存在“近视”缺陷，对理解模型智能边界有重要启发。
arXiv:2605.06840v5 Announce Type: replace Abstract: Large language models (LLMs), especially reasoning models, generate extended chain-of-thought (CoT…