Skip to content

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

Oct 13 · Tuesday

All papers

Found 10 papers
Filter5

Attack type

Jailbreaks35Prompt injection10Poisoning and backdoors8Detection evasion9Malicious use3

Attack technique

Gradient and representation optimization3Cross-modal payloads4

Impact

Unauthorized actions3Output manipulation7

System type

Models and APIs5AI Agent14coding agent1web agent6Browser and computer use4

Attack surface / entry point

Web pages and interfaces3Images, audio and video9

Layer

Prompt layer4Application layer5

System component

MCP and skills16Memory4Guardrails and judges6Monitors11Reasoning chains3Permissions and sandboxing8Vision10Multimodal11
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：Prompt injectionSystem type：Models and APIsSystem type：coding agentSystem type：Browser and computer useSystem component：VisionClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2610.09027

    P-VMI：对抗图像经 KV cache 持续影响多轮对话

    提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出

    arXiv
    2610.09027
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, Qwen3-VL-8B-Instruct, Gemma-4-12B

    Abstract论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2610.06898

    DIBench：面向移动 GUI 智能体多候选选择决策完整性的安全基准

    用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性

    arXiv
    2610.06898
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    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。

    Paper analysisRead analysis
  4. 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
  5. Evaluation and benchmarksarXiv 2609.04859

    MM-IFEval-Pro：面向视觉语言模型的多语言抗攻击指令遵循基准

    提出抗攻击多语言视觉指令遵循基准 MM-IFEval-Pro

    arXiv
    2609.04859
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-VL-8B-Instruct, InternVL3.5-8B, MiniCPM-V4.5 and others5
    AbstractMM-IFEval-Pro 以规则验证评测中英指令遵循与视觉劫持，GRPO 提高两基座平均分。

    MM-IFEval-Pro 是面向 VLM 的中英多模态指令遵循基准，并配有可用规则计算奖励的 GRPO 训练集。

    Paper analysisRead analysis
  8. DefensesarXiv 2603.14707

    Visual Confusion Agents: Exploiting and Defending Against Perception Failures in Computer-Use Agents

    Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents

    arXiv
    2603.14707
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    multi-modal-embed-small
    AbstractPerception 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.

    Paper analysisRead analysis
  9. AttacksarXiv 2602.15927

    研究者提出面向多轮对话的视觉记忆注入攻击 VMI

    提出 VMI，用扰动图像在多轮对话中潜伏并仅在触发话题输出预定消息

    arXiv
    2602.15927
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-VL-7B-Instruct, Qwen3-VL-8B-Instruct, LLaVA-OneVision-1.5-8B-Instruct and others5
    AbstractVMI 让扰动图像在多轮 LVLM 中潜伏，作者称触发话题出现后仍可输出预定消息。

    VMI 是面向多轮 LVLM 的定向图像攻击：第三方发布带小扰动的图像，良性用户把它当作普通输入。

    Paper analysisRead analysis
  10. DefensesarXiv 2602.10915

    Blind Gods and Broken Screens: Building a Secure, Intent-Centric Mobile Agent Operating System

    Proposes Aura, which uses a trusted kernel to mediate the identity, perception, and action control of mobile agents

    arXiv
    2602.10915
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    Gemini-3-Flash
    AbstractAura mediates structured interactions via the Agent Kernel.

    Aura uses kernel-mediated structured agent interaction, replacing screen-interface mobile assistants..

    Paper analysisRead analysis
You have reached the end