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 technique

Automated search3Encoding and obfuscation4Role-play and persuasion3Defense-targeted3

Impact

Harmful content7Unauthorized actions6Output manipulation3

System component

Guardrails and judges3Fine-tuning and open weights3Multimodal3
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 technique：Defense-targetedImpact：Output manipulationSystem component：Guardrails and judgesClear all

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

  1. AttacksarXiv 2609.30383

    研究者提出技能级联攻击

    提出技能级联攻击，把有害目标拆散到多个技能里绕过单技能扫描

    arXiv
    2609.30383
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.4 Mini, Claude Opus 4.6 and others11

    Abstract论文探讨了多技能智能体系统面临的技能级联攻击风险，提出自动化红队框架与基准集，指出跨技能交互存在安全防护盲区。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.08236

    研究：内容不变的风格包装可翻转 LLM 安全评判器的判定

    提出内容不变样式包装，翻转安全评审器的判定

    arXiv
    2609.08236
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-4o-mini (gpt4o), GPT-4o-mini (strongreject), DeepSeek-Chat and others7
    Abstract论文揭示特定安全评审器易受保持内容不变的外层包装诱导改变判定，并指出安全评估应将判定稳定性作为重要考量指标。

    这是一项关于大语言模型自动化安全评审系统表面样式脆弱性的评估研究。

    Paper analysisRead analysis
You have reached the end