Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack type

Jailbreaks3

Attack technique

Automated search3

Impact

Harmful content3

System type

Models and APIs3

Attacker access

Black-box83Gray-box3White-box15

Layer

Prompt layer3
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.
Impact：Harmful contentAttacker access：Gray-boxLayer：Prompt layerClear all

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

  1. AttacksarXiv 2607.02961

    研究者提出信息过载方法越狱大型视觉语言模型

    提出 INFER+ 信息过载方法，越狱大型视觉语言模型

    arXiv
    2607.02961
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box, Gray-box
    Evaluated models
    Qwen3-VL-8B, Qwen2-VL-7B, InternVL3.5-8B and others8
    Abstract用图文过载越狱 LVLM。

    这篇工作用信息过载越狱 LVLM，而不是靠 OOD 变换隐藏意图。

    Paper analysisRead analysis
  2. AttacksarXiv 2607.21619

    ASO：用GRPO优化视觉风格放大MLLM越狱攻击

    提出 ASO，用 GRPO 优化视觉风格以放大越狱攻击

    arXiv
    2607.21619
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    GPT-4.1-mini, Gemini-2.5-Flash, Qwen3-VL and others6

    Abstract论文揭示了 MLLM 的风格敏感性脆弱面，提出 ASO 框架利用强化学习优化风格触发器，有效放大了现有视觉越狱效果。

    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