Skip to content

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

Oct 12 · Monday

All papers

Found 78 papers
Filter3

Attack type

Jailbreaks30Prompt injection19Poisoning and backdoors9Extraction and theft3Detection evasion9

Attack technique

Gradient and representation optimization27Automated search11Multi-turn escalation7Encoding and obfuscation13Reasoning-chain manipulation4Cross-modal payloads49Defense-targeted6Dormant triggers6

Defense type

Permissions and approval3

Impact

Harmful content29Unauthorized actions12Data and privacy leaks5Output manipulation25Availability and reliability4Oversight failure3

System type

Models and APIs47LLM applications5AI Agent26coding agent4web agent4Embodied systems and robotics4

Attacker access

Black-box23Gray-box5White-box4

Attack surface / entry point

User input36Web pages and interfaces4Tool responses4Tool and skill descriptions6Inter-agent messages3Images, audio and video55Training data3Distribution channels3

Layer

Prompt layer47Application layer26Training and data layer3

System component

MCP and skills38Memory24RAG26Guardrails and judges55Monitors6Reasoning chains23Permissions and sandboxing12Fine-tuning and open weights29Vision60Audio13Video3Image generation22Embeddings9Multimodal96
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
System component：MonitorsSystem component：Permissions and sandboxingSystem component：VisionClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  3. 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
  4. 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
  8. AttacksarXiv 2610.00392

    A2A-TIBA：针对 A2A 协议 LLM 智能体的间接提示注入攻击与三层同构攻防模型

    提出 A2A-TIBA，经 A2A 对等任务间接注入并植入常驻回调

    arXiv
    2610.00392
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    MiniMax-M3, deepseek-v4-pro, glm-5.3 and others8
    AbstractA2A-TIBA 一次植入后绕过智能体，GDA 用四类结果定位防线，ELA-ITL 把信封标注列为第三层。

    A2A-TIBA 把间接提示注入和绕过放进 A2A：gray-box 攻击者已能投递任务，诱导目标部署常驻回调程序后，下令和外传不再经过智能体。

    Paper analysisRead analysis
  10. 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
  11. AttacksarXiv 2609.34518

    SEAD 论文提出工具型 Agent 的状态视角攻击与防御方法 DART 与 SAGE

    提出工具型 Agent 的自适应攻击 DART 与预执行防御 SAGE

    arXiv
    2609.34518
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Luna, GPT-5.6 Terra, Gemini 3.8 Flash and others5

    Abstract论文提出状态控制框架 SEAD、攻击 DART 与防御 SAGE，实验显示执行反馈与环境探测在攻防交互中具有关键作用。

    Paper analysisRead analysis
  14. 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
  15. 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
  16. AttacksarXiv 2609.14003

    FlowSeal：用信息流控制阻断 LLM Agent 的隐私泄露

    提出 FLOWSEAL，用工具级信息流控制阻断智能体隐私泄露

    arXiv
    2609.14003
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V3.2, GPT-4.1-mini, Gemini-Flash-2.5

    Abstract作者分析大模型智能体隐私检查与攻击面重合问题，提出外部拦截防御 FLOWSEAL 并验证有效性。

    Paper analysisRead analysis
  17. AttacksarXiv 2609.11757

    Researchers disclose a Whisper prompt injection attack on the AP2 payment protocol and propose the A-VIP defense

    提出 AP2 支付协议的 Whisper 攻击与 A-VIP 绑定防御

    arXiv
    2609.11757
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gemini-2.5-flash-lite, gemini-3.1-flash-lite, gemini-3-flash-preview and others15

    Abstract论文揭示了 AP2 协议决策层受操纵的风险，提出结构化与权能绑定防御 A-VIP，并发布评测基准。

    Paper analysisRead analysis
  18. AttacksarXiv 2609.07048

    FreqDoor：面向视觉语言模型的频域后门攻击

    提出 FreqDoor，在频域混合振幅并对生成式 VLM 做训练时视觉后门

    arXiv
    2609.07048
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    BLIP-2 (opt-2.7b), InstructBLIP (flan-t5-xl), LLaVA (interleave-qwen)
    AbstractFreqDoor 用频域振幅混合给三款 VLM 植入仅视觉的训练时后门。

    FreqDoor 是针对生成式 VLM 的仅视觉、训练时后门：在频域混合触发源振幅、保留干净图像相位，使触发在空间上分散。

    Paper analysisRead analysis
  19. AttacksarXiv 2609.04533

    Repeat-After-Me：针对黑盒 VLM 的自适应视觉提示注入攻击

    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

    arXiv
    2609.04533
    Published
    Layer
    Application layer
    Setting
    AI Agent
    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。

    Paper analysisRead analysis
Load more