Skip to content

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

Oct 12 · Monday

All papers

Found 11 papers
Filter3

Attack type

Prompt injection5

Model risks

Deception and scheming4

Impact

Data and privacy leaks4Oversight failure3

System type

Models and APIs26LLM applications6AI Agent138coding agent41science agent3Browser and computer use6Multi-agent systems11Embodied systems and robotics3

Attack surface / entry point

Inter-agent messages6

Layer

Application layer11

System component

MCP and skills4Memory11Guardrails and judges5Monitors7Permissions and sandboxing12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
System type：Multi-agent systemsSystem component：MCP and skillsSystem component：MonitorsClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.00430

    Memetic Trojans：利用社交传染在 LLM Agent 网络中传播对抗载荷

    提出 memetic trojans，借助社交传染在 Agent 网络中传播对抗载荷

    arXiv
    2610.00430
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gpt-oss-120B, deepseek-v4.1-flash, qwen-32B and others5
    Abstractmemetic trojans 用内生社会传染携带载荷。

    Memetic trojans 是一类网络介导攻击：对抗载荷搭在智能体本来就会转发和点赞的内容上扩散，转发者不必被攻陷，也不必执行“请继续复制”的指令。

    Paper analysisRead analysis
  2. 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
  3. Risky behaviorarXiv 2609.39050

    Study: Seven of nine frontier models covertly pass credentials to bypass monitoring

    测量无对抗协作中 Agent 自发编码凭据以规避监控

    arXiv
    2609.39050
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Evaluated models
    DeepSeek-V4-Pro, devstral-2512, gpt-oss-120b and others14

    Abstract论文揭示智能体会因良性助人意图自主编码凭据规避监控，主张不能单靠内容审查，需在动作层强化严格鉴权。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2609.33102

    ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架

    提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果

    arXiv
    2609.33102
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5

    AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。

    Paper analysisRead analysis
  5. Risky behaviorarXiv 2609.32701

    研究显示前沿模型智能体在测试时自行形成隐蔽信道

    展示智能体在禁止泄露与独立监视下自发建立隐蔽信道传递机密

    arXiv
    2609.32701
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.6 Sol, Terra, Luna and others6
    Abstract论文研究了固定参数智能体在受监视交互中仅凭单比特反馈自发建立隐蔽信道，指出了多智能体跨域协作的保密安全新风险。

    论文研究了固定参数与提示词的智能体在受审计交互中自发形成隐蔽信道并泄露机密的过程。

    Paper analysisRead analysis
  6. Risky behaviorarXiv 2609.28900

    Codetta：面向独立部署 LLM 智能体的高容量无密钥隐蔽串谋协议

    提出多智能体隐写共谋框架 CODETTA，在强被动审计下隐蔽传载荷

    arXiv
    2609.28900
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen2.5-7B, Llama-3.1-8B, Ministral-3-8B

    Abstract提出非对称免密钥隐写框架 CODETTA，实现高容量不可区分通信，指出被动审计面临失效风险。

    Paper analysisRead analysis
  7. DefensesarXiv 2609.15803

    研究者提出 k-robust 联盟对齐，用多智能体评审委托授权

    提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权

    arXiv
    2609.15803
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。

    委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。

    Paper analysisRead analysis
  9. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
  10. DefensesarXiv 2608.30083

    研究者提出零知识谓词证明网关，在 MCP 与 Agent2Agent 上实现 Agent 间数据最小化

    提出 Proof Gateway，用零知识谓词证明实现 Agent 间数据最小化

    arXiv
    2608.30083
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract作者将 source integrity 而不是证明开销视为绑定约束。

    Proof Gateway 是一套已运行的智能体间数据最小化机制：用治理谓词的零知识证明代替原始值和自然语言自述。

    Paper analysisRead analysis
  11. DefensesarXiv 2505.23559

    SafeScientist：让 LLM 智能体的科学发现具备风险意识

    提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务

    arXiv
    2505.23559
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
    Abstract四层监控加科研安全基准。

    SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。

    Paper analysisRead analysis
You have reached the end