Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 15 papers Another 232 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.
Propose KVeil, which adds perturbations to face videos to prevent unauthorized customization from reproducing identity
Published Oct 9
Evaluated models Wan2.2-TI2V-5B , HunyuanVideo-1.5 , Kling 3.0 and others4 Abstract KVeil adapts LETHE's reference-reading disruption to the challenge's two stages, ranking first on the leaderboard in both Final columns.
提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果
Published Sep 27
Evaluated models GPT-5.4 , Claude Sonnet 4.6 , Qwen3-235B and others5 Abstract ORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。
提出 SkillDRE，用预执行与运行时双阶段反馈演化恶意 Agent 技能
Published Sep 26
Evaluated models DeepSeek-V4-Pro , GLM-5.2 , Qwen3.5-397B-A17B and others4 测试编程智能体被诱导或自主篡改自身执行轨迹的行为
Published Sep 25
Evaluated models GPT-5.6-Sol , GPT-6-Sol , Opus-5 and others11 Abstract 论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。
构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性
Published Sep 24
Evaluated models AdaBoost , XGBoost , TabPFN and others10 Abstract ACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。 。
提出移动 Agent 轨迹审计器 MATE，判断轨迹是否违反可编辑安全策略
Published Sep 19
Evaluated models MATE-0.5B , MATE-1.5B , MATE-3B Abstract MATE 用合成轨迹微调轻量审计器，在可编辑策略下判断移动智能体轨迹是否违规并给出解释。MATE 是面向移动 GUI 智能体的轻量策略条件轨迹审计器，在给定自然语言安全策略时判断轨迹是否违规并解释原因。
提出 MOLE 基准，评测监控器对 AI 智能体内部威胁的检出能力
Published Sep 7
Evaluated models GPT-5.3 Chat , GPT-5.5 , GPT-4.1 and others15 Abstract MOLE 构建了智能体内部威胁检测基准，作者指出高漏检现状与推理痕迹的防御价值，并展示了监控策略优化空间。MOLE 是首个针对前沿 AI 实验室智能体内部威胁检测的开放基准，旨在评估在有限每日审查预算与日常研发业务背景下识别恶意账号的能力。 。
提出 ClawSentry 多层监控网关，在技能准入和运行时拦截恶意技能与隐藏指令
Published Aug 21
Evaluated models Codex/GPT-5.4 , Codex/GPT-5.5 , Claude Code/GLM-5.1 and others6 Abstract ClawSentry 用包准入、三级运行时门控和反绕过，压低 skill 攻击并保住干净任务。ClawSentry 是挂在智能体运行时之外的安全监督网关，用来同时盖住 skill 执行的多个生命周期边界，并把已被拒绝的效果记到会话里。
提出 S³，用 guard agent 编排阶段安全技能防御智能体多阶段风险
Published Aug 3
Evaluated models DeepSeek-V4-Pro , DeepSeek-V4-Flash Proposes MTGuard, which blocks unsafe tool calls by comparing MCP call declarations with execution traces.
Published Jul 28
Evaluated models DeepSeek-V4-Flash , DeepSeek-V4-Pro , GPT-5.6 Luna 提出 Agent MechSuits，对多轮 CLI Agent 做步级检测与子空间转向
Published Jun 22
Evaluated models LLaMA-3.1-8B , Qwen-2.5-7B , Gemma-2-9B Abstract 白盒步级探针加稀疏转向可压低三模型恶意动作，同时提高生成崩溃率。Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御，并配有可执行轨迹基准 MAS。
提出 VPH 与 VTH，只改视频帧劫持世界模型并投毒下游策略
Published Jun 8
Evaluated models Cosmos-Predict 2.5 , Cosmos-Predict 2.5 AC , Dino WM and others4 Abstract 只改视频帧经世界模型投毒。只改看似安全的视频帧，经世界模型之后才改变下游机器人策略。 问题在于世界模型进入数据生成后，数据集检查看到的仍是安全演示，合成轨迹却可以变危险。
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。 。
提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP
Published May 17 Abstract 提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。
提出 Meerkat，聚类并搜索 Agent 轨迹库以定位跨轨迹安全违规
Published Apr 14
Evaluated models GPT-5.4 , GPT-5.4-mini , Qwen3.5-397B-A17B and others5 Abstract Meerkat 用聚类与智能体搜索定位跨轨迹违规，并在真实评测轨迹中找出脚手架泄题与奖励黑客。Meerkat 是事后审计方法，用来在智能体轨迹仓库里找出单条看不出、合在一起才违反自然语言安全属性的见证。
You have reached the end