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 type

Jailbreaks26Detection evasion2

Attack technique

Automated search6Encoding and obfuscation2Defense-targeted6

Attacker access

Black-box2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：Detection evasionAttack technique：Encoding and obfuscationAttacker access：Black-boxClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2606.09700

    The researchers propose the HPAA attack: bypassing 13 content moderation systems with typographic visual cues

    提出 HPAA 攻击，用排版视觉线索绕过内容审核系统

    arXiv
    2606.09700
    Published
    Layer
    Prompt layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    Llama-Guard-3-8B, Perspective API, ShieldGemma-2B and others13
    Abstract揭示了排版视觉线索与分词差异带来的审核盲区，HPAA 以极低查询实现近乎完全规避。

    这篇论文研究了人类视觉感知与大模型分词处理机制之间的差异所导致的内容审核漏洞。

    Paper analysisRead analysis
  2. AttacksarXiv 2509.09112

    研究：字符级扰动可破坏 LLM 水印，并提出基于遗传算法的去除攻击

    提出字符级扰动与遗传算法去除 LLM 水印

    arXiv
    2509.09112
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    OPT-1.3B, LLaMA-3-8B
    Abstract字符级扰动靠更大攻击范围移除水印。

    这篇工作评估推理时 LLM 水印在黑盒、有限查询下的移除难度，并比较字符级、token 级和句子级编辑。

    Paper analysisRead analysis
You have reached the end