Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Attack type

Jailbreaks7Prompt injection19Poisoning and backdoors12Extraction and theft1Detection evasion8

Attack technique

Gradient and representation optimization1Side channels4Defense-targeted0

Layer

Application layer1Infrastructure layer0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack technique：Gradient and representation optimizationAttack technique：Defense-targetedLayer：Application layerLayer：Infrastructure layerClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2603.11132

    WebWeaver: Breaking the topology confidentiality of LLM multi-agent systems via covert context inference

    Propose WebWeaver, which compromises only a single agent and recovers the multi-agent communication topology from conversation context.

    arXiv
    2603.11132
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Llama 3.1 8B, Qwen 2.5 7B, Mistral NeMo 12B and others6
    AbstractWebWeaver infers topology from context.

    WebWeaver is an inference attack against the confidentiality of LLM-MAS communication topology: it controls only one arbitrary agent and recovers the full graph from dialogue context, rather than querying agent IDs.

    Paper analysisRead analysis
You have reached the end