Skip to content

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

Oct 12 · Monday

Jailbreaks and attacks · Papers

Found 2 papers
Filter2

Attack technique

Automated search3Cross-modal payloads2

Attacker access

Black-box25Gray-box2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack technique：Cross-modal payloadsAttacker access：Gray-boxTopic: Jailbreaks and attacksClear all
  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
You have reached the end