Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 28 papers Another 213 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.
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
Published Oct 8
Evaluated models LGWM 开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知
Published Oct 7
Evaluated models CLIP ViT-B/32 , CLIP ViT-L/14 , Qwen2-VL-7B Abstract 论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。
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。
评测 ReAct 工具调用对多模态模型拒答有害请求的削弱
Published Oct 3
Evaluated models Gemini-2.5-Pro , Gemini-3.1-Pro-Preview , Claude Opus 4.6 and others13 Abstract 论文揭示了工具调用范式削弱 MLLM 拒答能力的现象，分析了稀释与偏移机制并验证了重注缓解方案。论文系统评估了智能体工具调用范式对多模态大语言模型拒答能力的影响，指出了工具增强视觉推理背后的安全隐患。核心探讨的问题在于：当 MLLM 从单次推理转向通过 ReAct 循环调用外部工具（打标、缩放、OCR、代码执行）时，工具使用机制本身是否会降低模型拒答有害请求的概率。
提出条件特征抑制防御，检出对抗补丁后抑制 VLA 内部特征
Published Oct 2
Evaluated models π0.5 , SmolVLA Abstract 条件抑制与 patch 相关的 SAE 特征，间歇攻击下可提高 SR，持续攻击下则不能。
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 测量并预测具身 VLM 规划器的任务拒答可变性
Published Sep 30
Evaluated models gemini-robotics-er-2-preview , gemini-robotics-er-1.6-preview Abstract 日常物体能翻转一部分已给出的拒答，可翻转程度取决于任务且可被本地代理预测。作者测量 constitution 守护的具身 VLM 规划器：一次拒答在只往场景里放一个日常物体之后还保不保持得住，并把这种易翻转程度称为任务的 malleability 。
提出 DrivingBench，评测通用视觉语言模型能否闭环驾驶真车
Published Sep 30
Evaluated models GPT-6 Astra , Claude Fable 5.1 , Grok 4.6 and others4 Abstract 仅 Astra 第二次跑完低速锥桶路线。DrivingBench 评测通用 VLM 能否自己闭环开真车，推理延迟也算进任务。
用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性
Published Sep 29
Evaluated models Qwen2.5-VL(32B) , Qwen3-VL(32B) , GUI-Owl(32B) and others7 Abstract 论文提出移动智能体决策完整性基准 DIBench，发现欺诈 UI 注入诱导目标选择并推高完成率，通用防御收益不稳定。
提出 Pictionary，将不可信文本渲染成图像以防御提示注入
Published Sep 29
Evaluated models Claude Opus 4.7 , Claude Haiku 4.5 , GPT-5.5 and others12 证明无显式危害的图文窄微调可诱发跨任务涌现未对齐
Published Sep 28
Evaluated models GPT-4o , GPT-4.1 , Gemini 2.5 and others15 Abstract 证实窄多模态微调可引发全面的多渠道未对齐行为转变，揭示了后训练阶段对齐被隐蔽重塑的安全隐患。论文系统探究了视觉-语言模型中由窄任务微调诱发的跨模态涌现未对齐（Emergent Misalignment, EM）现象。
提出 VoxParity，固定转写只改音频，评测语音智能体是否按行业规则改工具调用
Published Sep 28
Evaluated models MiMo-V2.6-Pro , gemini-3.7-flash , Qwen3.8-Omni and others15 Abstract VoxParity 用固定转写的音频对比和 words-only null，测量语音智能体是否按所听内容改变工具调用。VoxParity 测量语音智能体在词语不变、只有声音改变时，是否按行业规则改它所执行的工具调用。
提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作
Published Sep 28
Evaluated models GPT-5.6-sol , Kimi-K2.6 , Kimi-K3 and others6 Abstract 论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。
用 MMPIBench 评测多模态提示注入对 Agent 框架的影响
Published Sep 9
Evaluated models Claude Opus 4.8 , GPT-5.4 , Gemini 3.1 Pro and others6 Abstract 论文提出 MMPIBench 评测多模态提示注入对智能体的影响，发现模型主导行为、尝试远超完成，音频通道缺乏防护。
提出 Repeat-After-Me 自适应视觉提示注入，诱导 VLM 智能体执行指定任务
Published Sep 4
Evaluated models Claude-Opus-4.7 , GPT-5.5 , Gemini-3.1-Pro and others6 Abstract 论文提出了针对黑盒 VLM 的前缀诱导自适应视觉提示注入，在多款模型上诱发了工具调用与隐私泄露。
因果审计视觉工具调用，分离观察贡献与动作诱发捷径
Published Aug 7
Evaluated models DeepEyes , Pixel Reasoner , Mini-o3 and others6 Abstract 聚合增益集中在 Calibrated 少数轨迹，作者称之为视觉工具使用的错觉。对六个 thinking-with-images 模型做因果审计，检查 crop-and-zoom 返回的观察是否中介最终答案。
提出 HazardArena 基准，用孪生场景评测 VLA 的语义安全
Published Apr 14
Evaluated models OpenVLA-OFT , π0 , NORA and others4 Abstract safe-only 微调提升良性执行，也提升匹配不安全孪生上的危险完成。HazardArena 评测 VLA 在运动要求不变时，能否因语义风险而停手。
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.
Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents
Published Mar 16
Evaluated models multi-modal-embed-small Abstract Perception errors can be exploited by swapping screen pixels.The authors frame CUA's perception failure as a security vulnerability, visual confused deputy : the agent authorizes click(x,y) based on a misread screen, and the actual landing point differs from the element it believes it is clicking.