Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 22 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.
提出 CARE,离线认证 VLA 加速配置的回合级失败风险并选出最快合格候选
Published Oct 7
Evaluated models OpenVLA-OFT , π0.5 , π0 and others5 Abstract CARE 以配对回合认证加速诱发失败,在预算内选最快候选,不足则保留参考。CARE 在部署前从加速配置中选出最快、且加速诱发失败风险能被有限样本认证为低于用户预算的候选。证据不足就保留全计算参考策略。
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 TAPDreamer 用公开编码器做固定补丁。
Published Oct 6
Evaluated models FastWAM , DreamWAM-uncond , DreamWAM-joint and others4 提出 ControlPed 与 HazardPed,生成可控行人危险场景并评测端到端驾驶
Published Oct 5
Evaluated models DiffusionDrive , SSR , VAD and others7 提出轨迹级可迁移对抗攻击,降低深度强化学习策略的期望回报
Published Oct 5
Evaluated models DQN , Double DQN (DDQN) Abstract 轨迹级后退视界攻击在 CartPole 上比逐步 FGSM 类和 Sign 噪声更压低回报。这项工作研究 DRL 上的迁移式黑盒观测攻击 :受害参数不可访问时,在白盒代理上造扰动再迁移。
构建 AGENTDOXX 基准,评测联网搜索 Agent 对匿名访谈的再识别
Published Oct 5
Evaluated models GPT-5.6 Terra , GPT-5 Mini , GPT-4.1 Mini and others10 Abstract 论文提出了已知身份的重识别基准 AGENTDOXX,揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。
提出 Perturbot 扰动训练,打破 VLA 的模态捷径
Published Oct 3
Evaluated models π0.5 Abstract Perturbot 改训练数据以削弱三类模态捷径,GroundFscore 用来看成功是否来自任务证据。Perturbot 是一套不改推理的 VLA 训练期数据干预,用来削弱模态捷径,并用离线分数区分“任务变好”和“靠捷径变好”。
提出 WebFovea,加固视觉网页智能体的解析、执行、反馈与观察往返
Published Oct 2
Evaluated models claude-opus-4-6 提出 SceneFactory-3D,用路况反事实评测驾驶策略的闭环安全性
Published Oct 2
Evaluated models Frozen L0 , L0-T , L1 and others5 Abstract SceneFactory-3D 固定场景只改路况。SceneFactory-3D 是 GPU 批处理的多智能体驾驶仿真器,用来在场景和控制器固定时只改路面物理,并比较闭环结果。
提出 FAIL BANK,用运行时 CBF 反馈自进化更新 VLA 策略
Published Sep 30
Evaluated models π0.5 , π0 构建 AGENTTELL 基准,测量浏览器 Agent 的行为侧信道隐私泄露
Published Sep 27
Evaluated models Claude Sonnet 5 , Gemini 3.7 Flash , GPT-5.6 Luna and others6 Abstract 论文评估了浏览器智能体的行为侧信道泄露风险,并基于近万次会话提供了评测数据。
提出 UBA-ORL,以 BD/CM 样本在遗忘后激活离线 RL 后门
Published Sep 19
Evaluated models TD3+BC , BCQ , IQL Abstract UBA-ORL 用竞争的 BD/CM 样本,使离线 RL 后门在删除伪装轨迹后激活。UBA-ORL 研究离线强化学习中由合规轨迹删除激活的后门:合法贡献者同时上传共享触发的后门轨迹和伪装轨迹,训练后触发响应被压低,删除伪装批次后再升高。受害系统是使用静态数据集和轨迹级遗忘接口的离线 RL 服务。对手不能看到训练算法、参数、梯度或具体遗忘算法,但能提交可区分批次,并在部署时向观测注入预定触发。
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 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。
Proposes DAERT, which uses simulated failures as reward to generate diverse adversarial instructions, exposing VLA language vulnerabilities.
Published Apr 7
Evaluated models π0 , OpenVLA , OpenVLA-7B and others5 Propose SABER, which uses a reinforcement learning attacker to rewrite instructions within a budget to cause VLA task failure.
Published Mar 26
Evaluated models π0-LIBERO , π0.5 , X-VLA and others6 测量任务无关说服对 Agent 编码与网页研究行为的影响
Published Feb 1
Evaluated models gpt-4.1-nano , mistral-nemo-12b , llama-3.1-8b Abstract 任务无关说服会在轨迹上留下任务相关的行为痕迹,但立场易感性不能稳定预测其幅度。这篇工作测量一件事:与任务无关的说服进入对话之后,AI 智能体执行后面的编码或网页研究时,轨迹是否系统性不同,以及“更容易被说服”能否预测差有多大。