Skip to content

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

Oct 13 · Tuesday

All papers

Found 10 papers
Filter6

Attack type

Jailbreaks5Prompt injection58Poisoning and backdoors47Extraction and theft4Malicious use1

Attack technique

Cross-modal payloads3

Impact

Harmful content3Data and privacy leaks3

System type

LLM applications4AI Agent6

Attacker access

Black-box3

Attack surface / entry point

User input6Memory writes3Images, audio and video4

Layer

Prompt layer59Model layer15Application layer10Training and data layer5

System component

MCP and skills6Memory4RAG11Guardrails and judges12Monitors10Reasoning chains3Permissions and sandboxing8Vision3Embeddings3Multimodal6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack type：Extraction and theftAttack type：Malicious useLayer：Application layerSystem component：MemorySystem component：MultimodalClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  4. OtherarXiv 2609.12413

    SoK 综述：智能体 AI 时代的越狱攻击、防御与实践考量

    系统梳理智能体执行链路中的越狱攻击与防御并比较推理时防御

    arXiv
    2609.12413
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.5-4B, Llama-3.1-8B-Instruct
    AbstractSoK 将越狱重放到智能体流水线，并用两种模型检验回复层防御的边际与代价。

    Mia 等人把越狱安全从单轮回复扩展到智能体的规划、记忆、工具和智能体间通信，并问既有结论在更强原生对齐下是否还成立。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2608.03272

    多智能体协同过滤系统的连接性攻击与防御研究

    复现 AgentCF 上的多智能体攻防并刻画连通性作用

    arXiv
    2608.03272
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
    Abstract连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。

    作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。

    Paper analysisRead analysis
  6. AttacksarXiv 2606.09084

    研究者提出 Context-Fractured Decomposition 攻击

    提出 CFD 跨会话分解攻击，利用工件来源缺口绕过工具型 Agent 的本地检查

    arXiv
    2606.09084
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4.1, GPT-5-nano, Claude-3.5-Sonnet and others6
    AbstractCFD 用无指令 artifact 把越狱拆到跨会话。

    CFD针对工具型 LLM 智能体：利用 artifact 来源不被跟踪这一部署失败模式，把有害目标拆开后延迟组合。

    Paper analysisRead analysis
  8. DefensesarXiv 2603.01544

    RA-Det：利用鲁棒性不对称检测 AI 生成图像

    提出 RA-Det，利用鲁棒性不对称检测 AI 生成图像

    arXiv
    2603.01544
    Published
    Layer
    Application layer
    Setting
    LLM applications
    AbstractRA-Det 把扰动下特征漂移差变成检测信号，平均 ACC 高于表中通用检测器，但不是每行最高。

    RA-Det 是合成图像检测器，用扰动下的表示稳定性差异代替外观痕迹。

    Paper analysisRead analysis
  9. AttacksarXiv 2602.07379

    Aegis: Governance, Integrity, and Security for AI Voice Agents

    Proposes the Aegis red-teaming framework for multi-turn attacks on high-risk voice agents.

    arXiv
    2602.07379
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
    AbstractAegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.

    Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.

    Paper analysisRead analysis
You have reached the end