Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter3

Attack type

Jailbreaks41Prompt injection17Poisoning and backdoors9Detection evasion8

Attack technique

Gradient and representation optimization11Automated search10Encoding and obfuscation6Role-play and persuasion3Reasoning-chain manipulation2Cross-modal payloads4Defense-targeted16

Impact

Output manipulation3

System type

Models and APIs5

Attack surface / entry point

User input7

Layer

Prompt layer6

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 265papers have no tags yet and are not included in filtered results.
Attack type：Detection evasionAttack technique：Encoding and obfuscationAttack technique：Reasoning-chain manipulationClear all

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

  1. AttacksarXiv 2609.27542

    研究者用控制 token 注入删除 gpt-oss-20b 推理链并绕过思维链监控

    提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控

    arXiv
    2609.27542
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  2. 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
  3. 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
  4. 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
  5. AttacksarXiv 2606.09700

    研究者提出 HPAA 攻击：用排版视觉线索绕过 13 个内容审核系统

    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