Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 24 papers
Filter5

Attack type

Prompt injection9

Attack technique

Gradient and representation optimization9Cross-modal payloads8

Impact

Unauthorized actions8Output manipulation7Availability and reliability5

System type

Models and APIs180LLM applications52AI Agent43coding agent1web agent10Browser and computer use5Embodied systems and robotics13

Attack surface / entry point

Web pages and interfaces7Images, audio and video11

Layer

Prompt layer3Model layer5Application layer14

System component

MCP and skills25Memory11RAG3Guardrails and judges14Monitors25Reasoning chains7Permissions and sandboxing15Fine-tuning and open weights5Vision19Multimodal21
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 248papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：web agentSystem type：Embodied systems and roboticsSystem component：RAGSystem component：MultimodalClear all

Another 248papers do not have category tags yet and are not included in filtered results.

  2. Analysis and theoryarXiv 2610.09517

    审计发现 CLIP 安全分数主要反映画面与提示词场景的相似度

    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

    arXiv
    2610.09517
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    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。

    Paper analysisRead analysis
  3. DefensesarXiv 2610.09469

    Secure-CUA: Constraining the Impact of Untrusted Content in Computer-Use Agents

    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

    arXiv
    2610.09469
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    Claude Opus 5, Gemini 3.8 Flash, GPT-5.6-Sol
    AbstractSecure-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。

    Paper analysisRead analysis
  4. AttacksarXiv 2610.09240

    WebMirage hijacks visual web agents' browser operations with adversarial images

    提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作

    arXiv
    2610.09240
    Published
    Layer
    Application layer
    Setting
    web agent
    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。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2610.05586

    AgentDoxx：联网搜索 Agent 对匿名访谈文本的再识别评测

    构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别

    arXiv
    2610.05586
    Published
    Layer
    Application layer
    Setting
    web agent
    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。

    Paper analysisRead analysis
  8. DefensesarXiv 2610.04616

    PerturBot 用扰动训练打破视觉-语言-动作模型的模态捷径

    提出 Perturbot 扰动训练，打破 VLA 的模态捷径

    arXiv
    2610.04616
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    π0.5
    AbstractPerturbot 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”。

    Paper analysisRead analysis
  11. Risky behaviorarXiv 2609.38971

    研究测量并预测具身 VLM 规划器中任务的拒答可变性

    测量并预测具身 VLM 规划器的任务拒答可变性

    arXiv
    2609.38971
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    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。

    Paper analysisRead analysis
  12. Evaluation and benchmarksarXiv 2609.38948

    DrivingBench 发布：让视觉语言模型驾驶丰田 Corolla 绕桩

    提出 DrivingBench，评测通用视觉语言模型能否闭环驾驶真车

    arXiv
    2609.38948
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    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。

    Paper analysisRead analysis
  13. Evaluation and benchmarksarXiv 2609.35912

    MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

    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

    arXiv
    2609.35912
    Published
    Layer
    Application layer
    Setting
    coding agent
    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。

    Paper analysisRead analysis
  14. AttacksarXiv 2608.10393

    DURA：用扩散模型生成自然对抗补丁攻击 VLA 机器人模型

    提出 DURA，用扩散模型生成自然对抗补丁操控 VLA 机器人动作

    arXiv
    2608.10393
    Published
    Layer
    Prompt layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA-7B, π0-FAST, openvla-7B
    AbstractDURA 用扩散潜空间轨迹生成自然补丁，白盒与黑盒都能把 VLA 导向指定动作。

    DURA 是针对 VLA 的扩散式、补丁内容不受限的机器人攻击，同时支持白盒梯度和只看动作输出的黑盒。

    Paper analysisRead analysis
  15. AttacksarXiv 2608.04565

    Researchers propose Breadcrumbing long-range attack that can hijack the evidence chain of DeepResearch-style search agents

    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

    arXiv
    2608.04565
    Published
    Layer
    Application layer
    Setting
    web agent
    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。

    Paper analysisRead analysis
  17. AttacksarXiv 2606.09499

    研究者提出针对世界模型的机器人学习管线投毒攻击

    提出 VPH 与 VTH，只改视频帧劫持世界模型并投毒下游策略

    arXiv
    2606.09499
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    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。

    Paper analysisRead analysis
  18. Evaluation and benchmarksarXiv 2604.12447

    HazardArena：面向 VLA 模型的语义安全评测基准

    提出 HazardArena 基准，用孪生场景评测 VLA 的语义安全

    arXiv
    2604.12447
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA-OFT, π0, NORA and others4
    Abstractsafe-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。

    Paper analysisRead analysis
  19. AttacksarXiv 2603.16960

    针对现代视觉语言模型的对抗攻击

    对开源视觉购物智能体实施商品图对抗攻击并诱导买错

    arXiv
    2603.16960
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    LLaVA-v1.5-7B, Qwen2.5-VL-7B
    AbstractThe 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.

    Paper analysisRead analysis
Load more