Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter3

Attack technique

Gradient and representation optimization3Automated search7Encoding and obfuscation0Selection manipulation1

Impact

Harmful content42Unauthorized actions12Data and privacy leaks7Output manipulation16Availability and reliability1
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 technique：Encoding and obfuscationAttack technique：Selection manipulationImpact：Availability and reliabilityClear all

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

  1. AttacksarXiv 2608.12273

    研究者提出 Convergent Detour Hijacking 攻击，可让技能型 LLM Agent 绕路并放大资源消耗

    提出 CDH 攻击，让技能型 Agent 绕路放大资源消耗

    arXiv
    2608.12273
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude-Haiku-4.5, DeepSeek-V4-Pro, DeepSeek-V4-Flash and others6
    AbstractCDH 让静态技能在保持任务完成时拉高调用与 token，耗时则因后端而异。

    CDH 是针对渐进披露技能智能体的发布者侧、纯文本攻击：一个静态协调器把本可正确完成的任务，拐进有界但更耗资源的技能绕路，再交还原任务。

    Paper analysisRead analysis
You have reached the end