Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 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 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器
Published Oct 7
Evaluated models CISCO , HSS , AUDITOR and others8 Abstract 论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。
提出 PRETEXT 攻击，迭代改写技能文本绕过技能扫描器并让 Agent 执行木马
Published Sep 30
Evaluated models glm (z-ai/glm-5.1) , qwen3t (qwen/qwen3-235b-a22b-thinking-2507) , gpt-oss (openai/gpt-oss-120b) Abstract 论文提出了针对多阶段技能检测器的白盒攻击，揭示了单纯依赖大模型自适应检测的局限。PRETEXT 是一项针对基于“静态规则加语义大模型”的智能体技能安全检测框架的白盒攻击与协同进化评估研究。
提出 Fed-ADR，用编排服务器协同操纵梯度攻破联邦学习并检测恢复
Published Sep 23
Evaluated models CNN（MNIST：2 Conv + 3 FC） , CNN（Fashion-MNIST：6 Conv + 1 FC） , ResNet18（CIFAR-10） Abstract Fed-ADR 用 gray-box 编排攻击绕过多种聚合防御，再用 Hessian 一致性检测和窗口内恢复把准确率拉回。Fed-ADR 是一套面向联邦学习的攻击、检测与恢复框架：编排服务器改写合谋客户端的梯度，使参数服务器的现有防御把投毒更新当成良性，同时在发现后用历史梯度把全局模型原地修回来。
提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器
Published Aug 10
Evaluated models GPT-5.5 , DeepSeek-V4-Pro , GLM-5.2 Abstract 论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
提出 CAVA，将异构智能体运行时事件规范为可哈希动作并绑定审批与回执
Published Jul 15 Abstract CAVA 用规范动作指纹承接异构运行时治理。CAVA 是给异构智能体运行时用的动作语义层，用来回答“被批准和被审计的到底是哪一个动作”。
构造可通过计费审计的 token 虚报，使服务商系统性超收
Published May 28
Evaluated models PALACE domain-adapted auditor Abstract 不诚实提供方可在三种 token 审计上虚报并通过检查，作者认为需改用提供方不控制的证据。不透明 LLM 的按 token 计费里，现有审计核验的是提供方可控的证据，不诚实提供方可以虚报并通过检查。 。
Attacks arXiv 2505.23266 · May 29, 2025 提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知
Published May 29, 2025
Evaluated models Lseg , Clip , ViT-L/16 and others5 Abstract AdvOF 以多视角融合生成对抗物体。AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。
You have reached the end