Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Attack technique

Gradient and representation optimization5Automated search11Encoding and obfuscation7Role-play and persuasion6Conversation structure manipulation3Cross-modal payloads3Side channels1Defense-targeted1Dormant triggers3

System type

Models and APIs26LLM applications2AI Agent20coding agent7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack technique：Side channelsAttack technique：Defense-targetedSystem type：LLM applicationsClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2610.09981

    研究：LLM 路由决策日志可推断用户医疗、自伤等敏感话题

    提出利用路由元数据推断敏感话题的侧信道攻击

    arXiv
    2610.09981
    Published
    Layer
    Infrastructure layer
    Setting
    LLM applications
    Evaluated models
    RouteLLM (BERT router), notdiamond-0001, Vela (vLLM Semantic Router)

    Abstract论文揭示并测量了 LLM 路由决策在无文本日志中的敏感话题泄露，验证了按类别公平性防御的有效性与边界。

    Paper analysisRead analysis
You have reached the end