Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 261 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
Published Oct 9
Evaluated models LAYA-TD , LAYA-EN , LAYA-ML and others5 Abstract The authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链
Published Oct 7 Abstract 形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。
提出 SBW，为 LLM Agent 轨迹做抗改写与伪造的语义行为水印
Published Oct 7
Evaluated models Qwen2.5-3B-Instruct , LLaMA-3.2-3B , Qwen2.5-7B and others5 Abstract SBW 在语义簇上做溯源水印，改写检测高于精确符号，链式重放仍开放。SBW 是免训练的智能体行为水印，把所有者标识放在离散动作选择上，而不是输出 token。
提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控
Published Sep 23
Evaluated models openai/gpt-oss-20b , google/gemma-4-26B-A4B-it , deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4 Abstract 论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。
You have reached the end