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

Automated search2

Attacker access

Black-box11Gray-box2

System component

Guardrails and judges2
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：Automated searchAttacker access：Gray-boxSystem component：Guardrails and judgesClear all

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

  1. AttacksarXiv 2608.09732

    ColluSkill 用跨技能组合绕过 Agent 技能扫描器

    提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器

    arXiv
    2608.09732
    Published
    Layer
    Application layer
    Setting
    coding agent
    Attacker
    Black-box, Gray-box
    Evaluated models
    GPT-5.5, DeepSeek-V4-Pro, GLM-5.2

    Abstract论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。

    Paper analysisRead analysis
  2. AttacksarXiv 2503.02174

    研究者提出对抗分词攻击，可在不改文本的情况下绕过 LLM 安全限制

    提出 AdvTok 对抗分词攻击，不改文本只改分词来越狱并规避安全分类器

    arXiv
    2503.02174
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    Llama3.2-1B, Llama3.2-3B, Llama3.1-8B and others7
    Abstract作者称非规范分词能躲开对齐并仍得到针对原请求的回复。

    作者用非规范分词攻击已对齐的子词 LLM：恶意字符串的字符不变，只改 token 边界。

    Paper analysisRead analysis
You have reached the end