Skip to content

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

Oct 12 · Monday

All papers

Found 40 papers
Filter4

Attack type

Jailbreaks15Prompt injection9Detection evasion5

Attack technique

Gradient and representation optimization27Automated search9Multi-turn escalation5Encoding and obfuscation13Conversation structure manipulation0Cross-modal payloads48Dormant triggers3

Impact

Harmful content15Unauthorized actions4Output manipulation19

System type

Models and APIs28AI Agent10web agent4Embodied systems and robotics4

Attacker access

Black-box12White-box3

Attack surface / entry point

User input16Web pages and interfaces4Images, audio and video37

Layer

Prompt layer30Application layer9

System component

MCP and skills7Memory4RAG6Guardrails and judges19Reasoning chains9Fine-tuning and open weights4Vision40Audio5Image generation7Embeddings3Multimodal52
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Encoding and obfuscationAttack technique：Conversation structure manipulationSystem component：VisionClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  2. 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
  3. 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
  6. AttacksarXiv 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
  8. 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
  10. AttacksarXiv 2606.12716

    PaperGuard：针对多模态 AI 同行评审的攻击与防御基准

    提出 PaperGuard，用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令

    arXiv
    2606.12716
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Claude-sonnet-4.5, GPT-4o, GPT-4.1 and others11
    AbstractPaperGuard 测到提示注入与白盒视觉抬分，并比较分块检索防御。

    PaperGuard同时评测并检测多模态 AI 审稿中的评分操纵。

    Paper analysisRead analysis
  11. AttacksarXiv 2606.01837

    论文提出 DSR 跨模态越狱框架：用良性输入诱导 MLLM 有害输出

    提出 DSR 跨模态越狱，用无害图文诱导 MLLM 生成有害图像

    arXiv
    2606.01837
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    gemini-2.5-flash-image, qwen-image-2.0, Tongyi Wanx 2.5
    AbstractDSR 用无害图文诱导商业 MLLM 输出有害图像，作者称组合能力会反过来扩大攻击面。

    DSR 是一种 black-box 跨模态越狱：输入侧不放显式有害内容，而让商业 MLLM 在推理中把无害图文重组成有害图像。

    Paper analysisRead analysis
  12. AttacksarXiv 2605.21541

    研究者提出 FRA-Attack 频域正则化方法，提升对闭源 MLLM 的迁移攻击效果

    提出 FRA-Attack，用频域对齐与梯度正则做可迁移定向视觉攻击

    arXiv
    2605.21541
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-5.2, GPT-5.4, Claude-Opus-4.6 and others15
    AbstractFRA-Attack 以频域对齐和梯度低通做可迁移定向攻击，闭源面板上作者称整体更强，Gemma 除外。

    FRA-Attack 是面向闭源 MLLM 的迁移式定向图像攻击。作者要解决的是：空间域局部对齐重复全局低频，代理梯度的高频成分又把更新拉向代理自身。

    Paper analysisRead analysis
  16. AttacksarXiv 2605.07399

    研究者提出 GPO-V，用全局概率优化越狱扩散视觉语言模型

    提出 GPO-V，用全局概率优化的视觉扰动越狱扩散视觉语言模型

    arXiv
    2605.07399
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    LLaDA-V, LaViDA
    Abstract作者用视觉扰动改 dVLM 的全局生成概率，以绕过两类拒绝。

    GPO-V 把越狱从“开头必须顺从”改成“整段去噪概率朝肯定方向走”。。

    Paper analysisRead analysis
  18. AttacksarXiv 2605.00583

    Jailbreaking vision-language models through the visual modality

    提出四类视觉越狱，把有害意图编码进图像以绕过安全拒答

    arXiv
    2605.00583
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-5.2, Claude-Haiku-4.5, Gemini-3-Flash and others8
    Abstract四类视觉越狱在六个 VLM 上检验文本对齐能否挡住视觉意图，模型与攻击之间差异大。

    四类视觉越狱用来检验前沿 VLM 的文本安全训练能否挡住由图像传达的有害意图。。

    Paper analysisRead analysis
  19. AttacksarXiv 2604.03117

    Unveiling Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models

    Proposes the universal curved mesh patch UCGP, causing cross-task semantic bias in infrared vision-language models.

    arXiv
    2604.03117
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    OpenAI CLIP ViT-L/14, OpenCLIP ViT-B/16, Meta-CLIP ViT-L/14 and others10
    AbstractUCGP uses one shared curved-grid patch to simultaneously lower the classification and open-ended outputs of IR-VLM.

    UCGP is a universal physical adversarial patch for infrared vision-language models. The question is: can a patch that can be attached and reused across samples cause stable semantic deviations in the infrared visual evidence shared by classification, description, and VQA. The patch is constrained to a low-frequency curved mesh.

    Paper analysisRead analysis
Load more