Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Attack type

Jailbreaks55Prompt injection21Poisoning and backdoors4Extraction and theft4Detection evasion9Malicious use5

Impact

Data and privacy leaks3

Attack surface / entry point

User input3

Layer

Prompt layer1Model layer5Application layer3Training and data layer3

System component

MCP and skills3RAG7Embeddings3Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftLayer：Prompt layerLayer：Application layerSystem component：MultimodalClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  3. AttacksarXiv 2602.07379

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

    提出 Aegis 红队框架，多轮攻击高风险语音 Agent

    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