Skip to content

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

Oct 13 · Tuesday

All papers

Found 6 papers
Filter5

Attack type

Jailbreaks5Prompt injection47Poisoning and backdoors15Extraction and theft5Detection evasion1

Impact

Data and privacy leaks4

System type

LLM applications3AI Agent3

Layer

Model layer3Application layer6

System component

MCP and skills7RAG11Guardrails and judges14Permissions and sandboxing3Vision3Embeddings3Multimodal5
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：Extraction and theftAttack type：Detection evasionLayer：Application layerSystem component：Permissions and sandboxingSystem component：EmbeddingsClear all

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

  2. DefensesarXiv 2609.04767

    SHAQ: Privacy-preserving retrieval in vector databases using shadow queries

    Proposes SHAQ, which replaces document embeddings with shadow query embeddings to defend against embedding inversion.

    arXiv
    2609.04767
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    GTR-T5 encoder, DPR
    AbstractSHAQ replaces document embeddings with shadow query embeddings.

    SHAQ is a defense against EIA for cloud vector databases: instead of directly modifying document embeddings, it replaces them with shadow query embeddings.

    Paper analysisRead analysis
  3. 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
  4. DefensesarXiv 2607.13716

    CAVA：面向智能体 AI 运行时治理的规范动作验证与证明

    提出 CAVA，将异构智能体运行时事件规范为可哈希动作并绑定审批与回执

    arXiv
    2607.13716
    Published
    Layer
    Application layer
    Setting
    AI Agent
    AbstractCAVA 用规范动作指纹承接异构运行时治理。

    CAVA 是给异构智能体运行时用的动作语义层，用来回答“被批准和被审计的到底是哪一个动作”。

    Paper analysisRead analysis
  5. AttacksarXiv 2607.01276

    研究者提出嵌入推断攻击 EIA，可在黑盒 IR 系统中识别所用嵌入模型

    提出嵌入推断攻击 EIA，在黑盒 IR 中识别所用嵌入模型

    arXiv
    2607.01276
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    e5-small, e5-small-v2, e5-base and others19
    AbstractEIA 用无序文档集的差异从候选中识别嵌入模型，并给出 reranker 与阈值下的计数。

    EIA 是在黑盒 IR 上识别所用嵌入模型的攻击。。

    Paper analysisRead analysis
  6. 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