Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter5

Attack type

Prompt injection4Poisoning and backdoors1

Attack technique

Gradient and representation optimization3Automated search15Encoding and obfuscation7Reasoning-chain manipulation1Defense-targeted5Dormant triggers37Selection manipulation8

System type

AI Agent1coding agent0Browser and computer use0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：Poisoning and backdoorsAttack technique：Reasoning-chain manipulationSystem type：AI AgentSystem type：coding agentSystem type：Browser and computer useClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2604.05549

    Stop obsessing over prompts: reasoning hijacking and constraint tightening for red-teaming LLM agents

    提出 JailAgent，不改用户提示，经推理劫持与记忆投毒操纵 Agent 动作

    arXiv
    2604.05549
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-3.5-turbo, GPT-4o, GPT-5 and others7
    AbstractJailAgent 不改提示词，用三阶段操纵推理与检索。

    JailAgent 是不修改用户原始提示词的 LLM 智能体红队框架。

    Paper analysisRead analysis
You have reached the end