Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter4

Attack type

Jailbreaks55Prompt injection6Poisoning and backdoors4Detection evasion8

Attack technique

Gradient and representation optimization3Automated search6Encoding and obfuscation6Defense-targeted5

Impact

Output manipulation5

System type

Models and APIs5LLM applications3

Attack surface / entry point

User input8Images, audio and video9

Layer

Prompt layer5

System component

Guardrails and judges4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Attack type：Detection evasionAttack technique：Gradient and representation optimizationAttack technique：Encoding and obfuscationAttack surface / entry point：User inputClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. InterpretabilityarXiv 2609.24801

    研究用 XAI 归因分析 Prompt Guard 2，同义词替换可翻转其提示注入判定

    用词级归因指导同义词替换，翻转提示注入检测并验证越狱

    arXiv
    2609.24801
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Prompt Guard 2 (86M), Llama 3.1 8B

    Abstract作者称检测靠分散的词法线索。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.05843

    SinoGlyphBench：中文字形混淆下语言模型审核的诊断基准

    提出 SinoGlyphBench，用配对字形混淆诊断中文审核稳定性

    arXiv
    2609.05843
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-5.4 mini, GPT-5.5, DeepSeek V4 Flash and others12
    AbstractSinoGlyphBench 显示中文字形混淆会同时增加有害漏报和误报，全文扰动最重。

    SinoGlyphBench是一个配对诊断基准，用来看内容审核在可还原的中文字形混淆下是否还保持原决定。

    Paper analysisRead analysis
  4. 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
  8. 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