Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter4

Attack type

Detection evasion3

Attacker access

Black-box41Gray-box3White-box6

System component

Memory0Guardrails and judges2Monitors1Vision4Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Attacker access：Gray-boxSystem component：MemorySystem component：Guardrails and judgesSystem component：MonitorsClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.15989

    研究者提出 plan injection 攻击，可绕过思维链监控

    提出 plan injection 攻击，植入良性伪装计划以绕过思维链监视器

    arXiv
    2609.15989
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    Qwen2.5-Coder-7B-Instruct, Qwen3-8B, DeepSeek-R1-0528 and others6

    Abstract论文指出模型会将外部上下文中的伪装计划改写为自身推理，使思维链监视器失效甚至反向合理化恶意行为。

    Paper analysisRead analysis
  2. 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
  3. 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