Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 26 papers Another 233 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.
提出 Secure-CUA，用动作事务约束计算机使用智能体的不可信影响
Published Oct 7
Evaluated models Claude Opus 5 , Gemini 3.8 Flash , GPT-5.6-Sol Abstract Secure-CUA 用每步事务约束不可信影响，良性 TSR 接近 Vanilla-CUA。Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响，同时保留合法任务所需的不可信信息。
提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作
Published Oct 7
Evaluated models LLaVA-v1.5-13B , LLaVA-v1.6-34B , MiniCPM-o-8B and others6 Abstract 论文提出了针对网络智能体的端到端视觉红队框架 WebMirage，揭示了从视觉定位到浏览器执行的安全脆弱性。WebMirage 是一个面向视觉定位网络智能体的流水线感知端到端红队攻击框架。
提出 AdvSim2Real，协同训练网页智能体抵御页面注入
Published Oct 7
Evaluated models Qwen3.5-4B 提出 CredLeak-Bench，评测 Agent 面对钓鱼的凭据泄露与恢复
Published Oct 6
Evaluated models Claude Sonnet 5 , Claude Opus 4.8 , Gemini 3.6 Flash and others7 提出 Veer，在网页 Agent 执行前改写会造成未授权后果的网页状态
Published Sep 28
Evaluated models GPT-5.6-Luna , DeepSeek-V4-Flash 评测安全 Agent 在对抗性任务污染下的解题成功与开销
Published Sep 17
Evaluated models Gemma-4 31B , DeepSeek-V4 Flash , GPT-OSS 120B and others6 Abstract AgentLSD 用配对 web CTF 表明，欺骗性环境证据会改变安全智能体的解题率与工作量。AgentLSD 是一个对照框架，用来测量安全智能体在任务本身不变时，对对抗性任务污染的反应。
提出可验证操作卡 VAC，把智能体浏览器确认绑定到真实 DOM 操作
Published Sep 16
Evaluated models gpt-oss-120b , Gemini-2.5-Flash , GPT-4.1 and others6 提出 WebMCP-Phalanx，用能力凭证与双智能体隔离浏览器工具调用
Published Aug 25 Abstract Phalanx 用浏览器凭证绑定工具所有权，Q/P 分离拦住描述注入，工具名与返回值仍有残留。WebMCP-Phalanx 针对浏览器里的 WebMCP 智能体：在 SOP 下补工具所有权，并把语义检查从有工具权的执行中分开。
提出 LoginTrap，以网页弹窗诱导 Web Agent 提交敏感信息
Published Aug 5
Evaluated models GPT-4o , Gemini 3 Flash , Claude Sonnet 4 and others7 Abstract 揭示网络智能体在黑盒网页下的登录诱导风险，利用模糊测试生成话术并跨骨干和架构验证了隐私泄露威胁。
提出权威链劫持与轨迹引导策略演化，劫持搜索 Agent 的证据链
Published Aug 5
Evaluated models Qwen3.5-9B , Gemma4-31B , DeepResearch and others7 Abstract 论文揭示了多步搜索智能体在受限中间人操纵下的脆弱性，提出 ACH 策略与 TGSE 演化方法并完成系统验证。
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 用 MisKnow-Agent 评测深度研究智能体是否采纳误导文档结论
Published Jul 23
Evaluated models DeerFlow , WebThinker , Gemini Deep Research and others6 Abstract 论文通过 MisKnow-Agent 框架评估发现长程研究智能体易采纳误导性知识，且现有防御难以完全消除该现象。
Proposes Prismata, which uses critical-path annotation and mechanical isolation to constrain cross-site prompt injection in web agents.
Published Jul 9
Evaluated models gpt-5.4-mini , gpt-5.4 , gpt-5.4-nano and others7 提出 UCM，用 DOM 掩码与类型受限隔离模型隔开网页智能体与不可信内容
Published Jul 7
Evaluated models Claude Sonnet 4.5 , Claude Sonnet 4.6 , GPT-5.4 提出 WebTrap 三阶段陷阱，中途劫持浏览器 Agent 完成攻击后再返回用户任务
Published May 8
Evaluated models DeepSeek-V3.1-Terminus , Gemini-2.5-Flash , GLM-4.5-Air and others5 Abstract WebTrap 把攻击目标嵌进用户流程中途执行再返回。WebTrap 是针对长程网页与文件导航的中途劫持注入，目标是在完成攻击动作后仍回到用户任务。
提出面向智能体浏览器的 Web 威胁模型并复现混淆攻击
Published May 7
Evaluated models GPT-5 , Claude-Sonnet-4.6 , Kimi-k2p5 and others8 Abstract 作者提出面向智能体浏览器的 Web 威胁模型与攻击分类，测试显示传统混淆攻击可复现且能绕过现有防御。这篇论文研究了智能体浏览器在面临传统 Web 攻击者时的安全性问题，指出当前针对提示词注入的安全假设无法抵御基于正常 Web 交互模式的混淆攻击。
提出 eTAMP，用网页内容跨会话投毒 Web Agent 轨迹记忆并诱导越权操作
Published Apr
Evaluated models GPT-5-mini , GPT-5.2 , GPT-OSS-120B and others6 Abstract 论文提出了基于环境注入的跨任务记忆投毒攻击 eTAMP，作者报告智能体在环境压力下易感性增加且能力与安全并不协同。该论文评估了基于大语言模型的 Web 智能体在利用历史交互轨迹进行记忆增强时的安全脆弱性。
Conduct adversarial attacks on product images for open-source visual shopping agents and induce wrong purchases
Published Mar 17
Evaluated models LLaVA-v1.5-7B , Qwen2.5-VL-7B Abstract The authors state that LLaVA is easily induced by three attacks to buy the wrong item, while Qwen's correct purchase rate remains close to its clean condition.The authors compare the robustness of two open-source VLM shopping agents against image adversarial perturbations in a self-built e-commerce environment.
提出 PINA，迭代优化针对导航智能体的提示注入
Published Jan 20
Evaluated models GPT-3.5-turbo , GPT-4 , Balcı et al. [2] Abstract PINA 在黑盒下优化导航提示注入。PINA 是面向基于 LLM 的导航智能体、在黑盒条件下优化提示注入的框架。
构建 TRAP 基准，评测网页 Agent 被界面提示注入劫持任务的情况
Published Dec 29, 2025
Evaluated models GPT-5 , Claude Sonnet 3.7 , Gemini 2.5 Flash and others6 Abstract 论文提出了基于五维模块化攻击空间的 TRAP 基准，评估了六个模型在真实网页环境中的注入风险。研究定位 ：针对网页自主智能体易受外部界面提示注入攻击的问题，构建了基于真实网站克隆的模块化评测基准 TRAP。