Skip to content

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

Oct 13 · Tuesday

All papers

Found 4 papers
Filter5

Attack type

Jailbreaks60Prompt injection41Poisoning and backdoors10Extraction and theft4Detection evasion12Malicious use11

Impact

Data and privacy leaks3

Attack surface / entry point

User input3

Layer

Prompt layer1Model layer5Application layer3Training and data layer3

System component

MCP and skills3RAG8Monitors0Embeddings3Multimodal4
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 theftLayer：Prompt layerLayer：Application layerSystem component：MonitorsSystem component：MultimodalClear all

Another 215papers 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

    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