Skip to content

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

Oct 12 · Monday

All papers

Found 25 papers
Filter4

Attack type

Prompt injection22Poisoning and backdoors20

Attack technique

Automated search4Dormant triggers8

Defense type

Detection and filtering3Instruction–data separation4Permissions and approval3

Impact

Unauthorized actions9Data and privacy leaks3Output manipulation13

System type

LLM applications5AI Agent20Multi-agent systems3

Attack surface / entry point

User input33Web pages and interfaces12Documents and messages17Tool responses16Tool and skill descriptions5Code repositories and dependencies4Retrieval corpus28Memory writes36Inter-agent messages4Distribution channels4

Layer

Application layer25

System component

MCP and skills12Memory18RAG7Guardrails and judges14Monitors9Reasoning chains5Permissions and sandboxing21Vision13Multimodal13
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Web pages and interfacesAttack surface / entry point：Documents and messagesSystem component：MemorySystem component：RAGClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.11932

    A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text

    Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.

    arXiv
    2610.11932
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Grok, Doubao, ChatGPT and others10

    AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.

    Paper analysisRead analysis
  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
  4. 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
  5. AttacksarXiv 2609.38270

    VirusCascade：劫持 LLM 推荐智能体的协同反思机制

    提出 VirusCascade，联合操纵商品描述与交互轨迹以劫持推荐智能体协同反思

    arXiv
    2609.38270
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    AgentCF, AgentSEQ, AgentRAG and others4
    Abstract作者把反思写回视为推广攻击入口，并用联合操纵和诊断探针研究其持续与传播。

    VirusCascade 是针对推荐智能体协作反思的 black-box targeted promotion 攻击研究。 攻击者只改商品描述和少量账号的普通交互，试图让目标商品获得更多良性用户曝光。

    Paper analysisRead analysis
  6. AttacksarXiv 2609.35576

    研究提出跨 LLM 助手的记忆跳跃攻击

    提出跨独立 Agent 的记忆跳跃攻击，经共享工件在助手间自传播

    arXiv
    2609.35576
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Luna, Kimi-K2.6, GPT-OSS-120B and others6
    Abstract论文证实持久工件与内存可形成跨智能体传播链，揭示了将共享工件纳入安全防线的重要意义。

    该论文系统研究并量化了通过共享持久工件在具有独立私有内存的 LLM 智能体之间发生自传播的“工件介导传播”攻击风险。

    Paper analysisRead analysis
  9. 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
  10. 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
  11. AttacksarXiv 2609.12448

    GraphProfiler 用个人知识图谱推断敏感属性并溯源到具体帖子

    提出 GraphProfiler，用个人知识图谱从帖子历史推断敏感属性并溯源

    arXiv
    2609.12448
    Published
    Layer
    Application layer
    Setting
    LLM applications
    AbstractGraphProfiler 用源链接个人知识图谱做属性推断，准确率接近文本基线，并把证据定位到少量源帖。

    GraphProfiler 是一个可审计的 LLM 敏感属性画像器：用源链接个人知识图谱，把推断落到具体帖子。

    Paper analysisRead analysis
  12. Evaluation and benchmarksarXiv 2609.02316

    Counter-GEO-Bench：现有护栏难挡 GEO 虚假信息

    构建 COUNTER-GEO-BENCH，评测生成式搜索中的 GEO 虚假信息防御

    arXiv
    2609.02316
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Gemma-4-31B-IT, Qwen-3.5-35B-A3B, Llama-4-Scout-17B-16E and others8

    Abstract论文构建了针对 GEO 虚假信息的首个防御基准，揭示通用护栏的失效与反作用，并提出了有效的轻量对比检测基线。

    Paper analysisRead analysis
  14. Evaluation and benchmarksarXiv 2608.09476

    ActBench：面向协作智能体行为安全的自演化基准

    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
  15. 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
  16. AttacksarXiv 2607.06595

    When Agents Remember Too Much: Memory Poisoning Attacks against Large Language Model Agents

    Proposed GhostWriter memory poisoning, which writes into the agent's long-term memory via email and calendar and activates across sessions

    arXiv
    2607.06595
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4-mini, DeepSeek-V4-Flash, Gemini-2.5-Flash and others4
    Paper analysisRead analysis
  17. AttacksarXiv 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
  18. DefensesarXiv 2606.24322

    Protecting LLM agent long-term memory from poisoning: tamper-evident, source-bound permissions and machine-checkable guarantees

    提出 TMA-NM，以写时来源绑定抵御 Agent 长期记忆投毒

    arXiv
    2606.24322
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gpt-5-chat, gpt-4o-mini, claude-opus-4.1 and others8
    AbstractTMA-NM 用来源绑定的行动权限挡住记忆洗白。

    TMA-NM 把 LLM 智能体长期记忆的行动权限绑到写时来源，用来挡住跨会话记忆投毒。

    Paper analysisRead analysis
  19. AttacksarXiv 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
  20. AttacksarXiv 2605.15338

    Hidden in Memory: Latent Memory Poisoning of LLM Agents

    提出潜伏记忆投毒，诱导 Agent 把外部文档写成持久伪造记忆

    arXiv
    2605.15338
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.5, Claude Sonnet 4.6 and others12
    Abstract持久记忆成为跨会话攻击面：通用载荷可写入伪造记忆，并在相关后续任务中影响行为。

    sleeper memory poisoning 研究带持久记忆的 LLM 助手：外部文档能否让助手存下一则伪造的用户记忆，并在原文档消失后的新会话里被取回、用来改变回复或动作。

    Paper analysisRead analysis
Load more