Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter3

Attack type

Jailbreaks21Prompt injection34Poisoning and backdoors63Model tampering8Extraction and theft2Detection evasion10

Attack technique

Gradient and representation optimization1Automated search6Side channels4Dormant triggers1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack technique：Gradient and representation optimizationAttack technique：Dormant triggersClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.33985

    研究：众包微调数据投毒可放大专有指令抽取

    提出主题锚点投毒，放大众包微调后的专有指令提取

    arXiv
    2609.33985
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, Llama-3.1-8B-Instruct and others4

    Abstract论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。

    Paper analysisRead analysis
  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
You have reached the end