# chain-of-thought
標記為「chain-of-thought」的 18 篇文章
操弄推理鏈
影響 AI 代理的 chain-of-thought 推理，將其規劃、決策與工具選擇導向攻擊者期望結果的技術。
思維鏈利用
利用模型思維鏈推論過程的攻擊,包括思維注入、指令遺忘與推論操弄。
推理模型攻擊
推理啟用 LLM 之安全風險概觀：思維鏈模型如何引入新攻擊面、利用原語與防禦挑戰。
Reasoning 模型 越獄s
How reasoning capabilities create novel jailbreak surfaces: chain-of-thought exploitation, scratchpad attacks, and why higher reasoning effort increases attack success.
Steganographic Reasoning
Hidden communication channels within AI reasoning traces, where models encode information or coordinate behavior through patterns invisible to human overseers, including detection methods and implications for AI safety.
Unfaithful Chain-of-Thought Reasoning
Analysis of unfaithful chain-of-thought reasoning in language models, where the visible reasoning trace does not accurately reflect the model's actual computational process, including detection methods, implications for oversight, and exploitation techniques.
推論模型利用
針對具推論能力模型的攻擊,包括 o1/o3 類模型以及其推論令牌利用。
紅隊演練推論軌跡
對可見推論軌跡模型進行紅隊演練的技術,包括思維注入與軌跡操弄。
推理模型中的注入
針對推理增強模型的注入攻擊研究,利用其思維鏈 (chain-of-thought) 與自我反思機制。
實作：推理模型漏洞利用
Attack reasoning models like o1, o3, and DeepSeek-R1 by exploiting chain-of-thought manipulation, reasoning budget exhaustion, and thought-injection 技術.
Reasoning Trace 利用 in CoT 模型
利用 visible chain-of-thought reasoning traces in models like o1與DeepSeek-R1 to manipulate outputs.
Reasoning Model Chain-of-Thought Exploitation
Exploit extended thinking and chain-of-thought reasoning in models like o1 and DeepSeek-R1.
實驗：思考鏈利用
利用思考鏈推理，洩漏模型內部推理、繞過安全過濾器、操弄決策過程。
推理模型安全性
推理模型 (如 o1、DeepSeek R1) 特有的安全性考量。
Reasoning Model Exploitation 詳解
Exploit extended thinking in reasoning models to inject false premises and manipulate conclusion generation.
Thought Injection for Reasoning 模型s
Techniques for injecting malicious content into chain-of-thought reasoning traces of thinking models, exploiting the gap between reasoning and safety enforcement.
Thought Injection in Reasoning Models 詳解
Inject adversarial thoughts into the reasoning chain of thinking models to manipulate final outputs.
Chain-of-Thought Hijacking 詳解
Walkthrough of hijacking visible reasoning traces in CoT models to redirect conclusions and bypass safety checks.