Skip to content

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

Oct 12 · Monday

All papers

Found 25 papers
Filter5

Attack type

Prompt injection19Poisoning and backdoors3

Attack technique

Gradient and representation optimization5Cross-modal payloads7

Defense type

Detection and filtering6Monitoring and auditing3

Impact

Unauthorized actions10Data and privacy leaks5Output manipulation5

System type

Models and APIs105LLM applications10AI Agent120coding agent8web agent7Browser and computer use4Multi-agent systems5Embodied systems and robotics9

Attacker access

Black-box4

Attack surface / entry point

User input54Web pages and interfaces32Documents and messages26Tool responses12Tool and skill descriptions26Code repositories and dependencies21Retrieval corpus25Memory writes5Images, audio and video13Training data4Weights and gradients4Distribution channels23Inference services and hardware3

Layer

Application layer25

System component

MCP and skills3Guardrails and judges7Monitors3Permissions and sandboxing3Vision9Multimodal12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
System type：LLM applicationsSystem type：coding agentSystem type：web agentAttack surface / entry point：Tool responsesAttack surface / entry point：Images, audio and videoClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.12292

    The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

    Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations

    arXiv
    2610.12292
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    LAYA-TD, LAYA-EN, LAYA-ML and others5

    AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.

    Paper analysisRead analysis
  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
  4. DefensesarXiv 2610.05870

    MBZUAI 提出可校准的真实图像认证方法

    提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动

    arXiv
    2610.05870
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    White-box

    Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。

    Paper analysisRead analysis
  5. DefensesarXiv 2610.05163

    Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark

    提出 PAA 方法，在边界动作前审计长流程智能体的分阶段提示注入

    arXiv
    2610.05163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
    Abstract论文针对长流程注入提出边界动作审计与 PAA，在保持低误阻的同时实现高拦截率。

    本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁，提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。

    Paper analysisRead analysis
  8. DefensesarXiv 2609.35659

    Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统

    提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改

    arXiv
    2609.35659
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (claude -p, version 2.1), 独立评审（同一 CLI，无工具）
    AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。

    Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。

    Paper analysisRead analysis
  9. 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
  10. Analysis and theoryarXiv 2609.23215

    研究审计 Active Inference Agent 的 LLM 解释器失败模式

    审计 Active Inference Agent 上 LLM 解释器的监督叙述失败

    arXiv
    2609.23215
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    GPT-4o, Claude-3-Opus, Gemini
    Abstract三组触发下解释流畅但错误，所提缓解都未被评估。

    作者审计的是挂在智能体上的运行时解释器，而不是智能体本身。操作员读到的是信念与动作的自然语言叙述。作者要问哪些可复现触发会让这段叙述失败，以及失败痕迹是什么样。

    Paper analysisRead analysis
  11. AttacksarXiv 2609.18217

    研究：跨通道碎片化攻击可绕过 MCP 单通道防御

    提出跨通道分段攻击，利用 MCP 隐式信任外发敏感文件

    arXiv
    2609.18217
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4o, GPT-4o-mini, GPT-5.4 and others15

    Abstract论文揭示了 MCP 多通道隐式信任层级，通过跨通道分段与协议级利用突破现有防御，展示了严重的凭证外发风险。

    Paper analysisRead analysis
  12. AttacksarXiv 2609.13889

    PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击

    提出 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私

    arXiv
    2609.13889
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    DeepSeek-V4-Flash, DeepSeek-V4-Pro, Qwen3-Max

    Abstract论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。

    Paper analysisRead analysis
  14. Evaluation and benchmarksarXiv 2609.05535

    Mind2Web-Injection：面向网页 Agent 视觉提示注入护栏的证据对齐评测

    提出 Mind2Web-Injection 评测网页 Agent 视觉注入护栏

    arXiv
    2609.05535
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    GPT-5.6-luna, Qwen3-VL-32B, Qwen3-VL-8B and others6
    Abstract作者称检测、定位和反事实响应在六个 VLM 上可分开。

    Mind2Web-Injection 用来检查网页截图护栏的判决是否对齐到该用的画面证据。。

    Paper analysisRead analysis
  15. DefensesarXiv 2608.24017

    WebMCP-Phalanx：为浏览器内 LLM Agent 工具调用建立信任边界

    提出 WebMCP-Phalanx，用能力凭证与双智能体隔离浏览器工具调用

    arXiv
    2608.24017
    Published
    Layer
    Application layer
    Setting
    web agent
    AbstractPhalanx 用浏览器凭证绑定工具所有权，Q/P 分离拦住描述注入，工具名与返回值仍有残留。

    WebMCP-Phalanx针对浏览器里的 WebMCP 智能体：在 SOP 下补工具所有权，并把语义检查从有工具权的执行中分开。

    Paper analysisRead analysis
  16. 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 2607.11698

    AHA 用自动研究循环发现生产 Agent 漏洞概念

    提出 AHA 自动科研循环，发现生产 Agent 的可复用漏洞概念

    arXiv
    2607.11698
    Published
    Layer
    Application layer
    Setting
    coding agent
    Attacker
    Black-box
    Evaluated models
    Minimax-M2.7, Kimi-K2.6, Deepseek-V4-Pro and others5
    Abstract论文提出基于可证伪科研循环的 AHA 框架，从生产级智能体中挖掘并沉淀漏洞概念图，提升攻击复用率并指导防御加固。

    AHA 是一项针对生产级 LLM 智能体自动化红队测试的研究，旨在解决传统方法仅保留具体攻击载荷而缺乏成因解释、导致跨版本复用困难且无法指导修复的问题。

    Paper analysisRead analysis
  18. DefensesarXiv 2606.22673

    Agent MechSuits：面向多轮 CLI Agent 的机制子空间安全引导

    提出 Agent MechSuits，对多轮 CLI Agent 做步级检测与子空间转向

    arXiv
    2606.22673
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    LLaMA-3.1-8B, Qwen-2.5-7B, Gemma-2-9B
    Abstract白盒步级探针加稀疏转向可压低三模型恶意动作，同时提高生成崩溃率。

    Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御，并配有可执行轨迹基准 MAS。

    Paper analysisRead analysis
  19. 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
  20. 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