Skip to content

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

Oct 13 · Tuesday

All papers

Found 22 papers
Filter4

Attack type

Prompt injection22Poisoning and backdoors7

Impact

Unauthorized actions12Data and privacy leaks5Output manipulation4

System type

LLM applications3AI Agent22coding agent3web agent3Browser and computer use1Multi-agent systems3

Attack surface / entry point

User input35Web pages and interfaces16Documents and messages22Tool responses24Tool and skill descriptions14Code repositories and dependencies7Retrieval corpus4Memory writes12Inter-agent messages8Images, audio and video5Distribution channels9

Layer

Application layer22

System component

MCP and skills4Memory6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.
System type：AI AgentSystem type：coding agentSystem type：Browser and computer useAttack surface / entry point：Documents and messagesClear all

Another 216papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2610.03153

    EvoRiskBench: An evolutionary benchmark for runtime security risks of workspace agents

    构建 EvoRiskBench 评测工作区 Agent 的运行时安全风险

    arXiv
    2610.03153
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Sol, DeepSeek-V4-Pro-0813, Claude Opus 5

    Abstract论文构建了工作空间智能体运行时风险基准 EvoRiskBench，发现高执行力智能体在 IPI 下面临较高安全风险。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.39146

    MADBench：多智能体辩论安全性评测基准发布

    提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响

    arXiv
    2609.39146
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gpt-4o, GPT-5, GPT-6 Astra
    AbstractMADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。

    MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2609.36817

    pikit：面向间接提示注入研究与评测的可组合工具包

    构建可组合工具包 pikit，评测编码智能体的间接提示注入

    arXiv
    2609.36817
    Published
    Layer
    Application layer
    Setting
    coding agent
    Abstractpikit 提供组合式间接注入评测。

    pikit 是面向间接提示注入研究的组合式工具包，主要贡献是组织攻击、投递通道、防御和判定流程，而非提出新的攻击优化算法。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2609.32691

    研究审计 Agent 安全评测缺陷：工具调用中介在间接提示注入下的有效评测框架

    提出卡点评测框架以审计智能体间接提示注入评测的测量缺陷

    arXiv
    2609.32691
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gpt-5.6-terra, llama3.1:8b, gemma4:12b and others4

    Abstract论文揭示了 IPI 评测中导致指标虚高的系统性缺陷，通过构建有效评测框架纠正了多项安全与模型能力结论。

    Paper analysisRead analysis
  8. Evaluation and benchmarksarXiv 2609.28915

    研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

    构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性

    arXiv
    2609.28915
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    AdaBoost, XGBoost, TabPFN and others10
    AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。

    ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2609.24662

    DUMA-Bench：评估 LLM Agent 安全的双控多智能体基准

    提出双控多智能体基准 DUMA-Bench，测量对抗环境下的策略违反

    arXiv
    2609.24662
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5, GPT-5-mini, GPT-5-nano and others14
    AbstractDUMA-Bench 用双控交互评测智能体安全。

    DUMA-Bench 把 τ²-bench 的双控交互做成智能体安全评测，用来看策略违反如何随用户、模型和环境一起出现。

    Paper analysisRead analysis
  10. Evaluation and benchmarksarXiv 2609.17320

    Emergence World：对长时程多智能体系统开展对抗压力测试

    提出 Emergence World，对长时程多智能体系统开展对抗压力测试

    arXiv
    2609.17320
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Claude Opus 4.8, DeepSeek v4 Pro, Gemini 3.5 Flash and others9

    Abstract作者通过长期平行世界实验指出模型对齐不具备可组合性，单模型群体会产生社会奉承、协同退缩及语言不透明等失效。

    Paper analysisRead analysis
  11. Evaluation and benchmarksarXiv 2609.09404

    MMPIBench：多模态提示注入对六种 Agent 框架的跨框架评测

    用 MMPIBench 评测多模态提示注入对 Agent 框架的影响

    arXiv
    2609.09404
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude Opus 4.8, GPT-5.4, Gemini 3.1 Pro and others6

    Abstract论文提出 MMPIBench 评测多模态提示注入对智能体的影响，发现模型主导行为、尝试远超完成，音频通道缺乏防护。

    Paper analysisRead analysis
  12. Evaluation and benchmarksarXiv 2608.09476

    ActBench: A Self-Evolving Benchmark for Behavioral Safety of Collaborative Agents

    构建自演化基准 ActBench，评测协作智能体的行为安全

    arXiv
    2608.09476
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude-Opus-4.8, Claude-Sonnet-4.6, GPT-5.5 and others15

    AbstractActBench 通过自演化搜索与双证据重构评测轨迹行为安全，揭示基础模型决策差异主导了协同智能体的操作风险。

    Paper analysisRead analysis
  14. Evaluation and benchmarksarXiv 2607.05189

    Researchers propose MemGhost, achieving covert memory injection into persistent personal agents

    提出 MEMGHOST，用单封邮件对持久个人 Agent 做跨会话隐蔽记忆注入

    arXiv
    2607.05189
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Claude Sonnet 4.5 and others6
    Abstract总结了论文的研究背景、双代理优化方法 MEMGHOST、全周期实验结果以及作者对记忆信任边界的启示。

    本文研究了持久化个人智能体面临的隐蔽记忆注入威胁，提出了一套兼顾写入、隐蔽与跨会话生效的自动化生成框架与全周期评测基准。

    Paper analysisRead analysis
  15. Evaluation and benchmarksarXiv 2606.04329

    研究者系统研究 LLM 智能体记忆投毒攻击并提出 MPBench 基准

    系统研究 LLM 智能体记忆投毒并构建基准 MPBench

    arXiv
    2606.04329
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Meta-Llama-3.1-70B-Instruct, Deberta-v3-base, Llama-3.1-8B-Instruct and others5

    Abstract系统研究了智能体记忆投毒风险，揭示了写入渠道漏洞，构建了 MPBench 基准并指出提示注入防御的局限。

    Paper analysisRead analysis
  16. Evaluation and benchmarksarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。

    Paper analysisRead analysis
  19. Evaluation and benchmarksarXiv 2601.21083

    OpenSec: Measuring Calibration of Incident Response Agents under Adversarial Evidence

    提出 OpenSec，评测事件响应 Agent 在对抗证据下的遏制校准

    arXiv
    2601.21083
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.2, Claude Sonnet 4.5, Gemini 3 and others5
    AbstractOpenSec 以执行评分测 IR 智能体在对抗证据下是否过度遏制，作者称缺口在克制。

    OpenSec 用 dual-control 事件环境测量 IR 智能体在对抗证据下的校准：分数看实际遏制，不看报告文本。

    Paper analysisRead analysis
  20. Evaluation and benchmarksarXiv 2512.23128

    牛津等发布 TRAP 基准

    构建 TRAP 基准，评测网页 Agent 被界面提示注入劫持任务的情况

    arXiv
    2512.23128
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5, Claude Sonnet 3.7, Gemini 2.5 Flash and others6
    Abstract论文提出了基于五维模块化攻击空间的 TRAP 基准，评估了六个模型在真实网页环境中的注入风险。

    研究定位：针对网页自主智能体易受外部界面提示注入攻击的问题，构建了基于真实网站克隆的模块化评测基准 TRAP。

    Paper analysisRead analysis
Load more