Skip to content

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

Oct 13 · Tuesday

All papers

Found 32 papers
Filter4

Attack type

Jailbreaks5Prompt injection10Detection evasion7

Attack technique

Gradient and representation optimization28Automated search10Multi-turn escalation5Encoding and obfuscation14Reasoning-chain manipulation4Cross-modal payloads52Defense-targeted5Dormant triggers3

Impact

Harmful content5Unauthorized actions3Output manipulation20

System type

Models and APIs20AI Agent10web agent4Embodied systems and robotics4

Attacker access

Black-box5Gray-box3White-box3

Attack surface / entry point

User input7Web pages and interfaces4Images, audio and video26

Layer

Prompt layer23Application layer8

System component

RAG5Guardrails and judges5Monitors3Reasoning chains16Vision29Audio4Embeddings3Multimodal35
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 technique：Gradient and representation optimizationAttack technique：Reasoning-chain manipulationSystem component：MonitorsSystem component：VisionClear all

Another 215papers 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 2609.27542

    Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

    提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控

    arXiv
    2609.27542
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  7. AttacksarXiv 2609.15989

    Researchers propose plan injection attack that can bypass chain-of-thought monitoring

    提出 plan injection 攻击，植入良性伪装计划以绕过思维链监视器

    arXiv
    2609.15989
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    Qwen2.5-Coder-7B-Instruct, Qwen3-8B, DeepSeek-R1-0528 and others6

    Abstract论文指出模型会将外部上下文中的伪装计划改写为自身推理，使思维链监视器失效甚至反向合理化恶意行为。

    Paper analysisRead analysis
  9. AttacksarXiv 2609.01023

    Akrasia：针对推理型代码 LLM 的隐蔽后门攻击

    提出隐蔽后门攻击 AKRASIA，在推理代码模型提示中植入触发器并伪装思维链

    arXiv
    2609.01023
    Published
    Layer
    Prompt layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, GPT-5.5, Gemini-3.5-flash and others7

    Abstract论文针对推理代码大模型提出了隐蔽推断期后门攻击 AKRASIA，揭示了模型思维链可被利用进行欺骗性伪装的安全隐患。

    Paper analysisRead analysis
  10. 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
  11. 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
  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
  15. 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
  16. 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
  19. AttacksarXiv 2603.16960

    Adversarial attacks against modern vision-language models

    Conduct adversarial attacks on product images for open-source visual shopping agents and induce wrong purchases

    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