Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack technique

Gradient and representation optimization1Encoding and obfuscation2Role-play and persuasion0

System type

AI Agent3

Attack surface / entry point

User input12Web pages and interfaces7Documents and messages8Tool responses6Tool and skill descriptions5Code repositories and dependencies3Retrieval corpus8Memory writes3Inter-agent messages3Images, audio and video8Distribution channels5

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationAttack technique：Encoding and obfuscationAttack technique：Role-play and persuasionAttack surface / entry point：Inter-agent messagesLayer：Application layerClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  2. 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
  3. AttacksarXiv 2603.00131

    Thought Virus: viral misalignment induced by subliminal prompts in multi-agent systems

    Propose Thought Virus, which propagates preferences along multi-agent messages via subliminal prompts.

    arXiv
    2603.00131
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct
    AbstractThought Virus spreads a single-point bias downstream.

    Thought Virus puts subliminal prompting into multi-agent communication, to see whether a single-point deviation spreads across the network without naming the target concept.

    Paper analysisRead analysis
You have reached the end