# o1
標記為「o1」的 4 篇文章
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。
reasoningo1chain-of-thoughtattacks
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.
reasoningjailbreakchain-of-thoughto1o3adaptive-attacksresearch
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.
labreasoningo1chain-of-thought
推理模型安全性
推理模型 (如 o1、DeepSeek R1) 特有的安全性考量。
modelsreasoningchain-of-thoughto1