Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter5

Attack technique

Gradient and representation optimization0Automated search4Conversation structure manipulation0Defense-targeted3Dormant triggers2

System type

Models and APIs32LLM applications3AI Agent12coding agent2

Attack surface / entry point

User input2Tool and skill descriptions3Weights and gradients3Distribution channels4
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 technique：Gradient and representation optimizationAttack technique：Conversation structure manipulationAttack technique：Dormant triggersSystem type：coding agentAttack surface / entry point：User inputClear all

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

  2. AttacksarXiv 2608.09577

    ElasticBack：通过触发词与规则耦合在 LLM Agent 技能中植入条件后门

    提出 ElasticBack，在单个 Agent 技能中植入条件后门

    arXiv
    2608.09577
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GLM-5.2, MiniMax-M3, GPT-5.4 and others4
    AbstractElasticBack 用冻结规则加遗传搜索演化 trigger，在单 skill 上做条件后门。

    ElasticBack 是放在 LLM agent 单个 skill 里的条件后门攻击。。

    Paper analysisRead analysis
You have reached the end