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 type

Jailbreaks9Model tampering2Extraction and theft1

Model risks

Inappropriate refusal3

Impact

Harmful content3

System type

Models and APIs3

Layer

Model layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack type：Model tamperingAttack type：Extraction and theftModel risks：Inappropriate refusalClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  2. InterpretabilityarXiv 2609.06934

    论文提出拒答的几何解释：事后安全训练脆弱，预训练期持续安全共训更抗攻击

    解释后验安全的权重几何脆弱性，并提出预训练持续安全共训练

    arXiv
    2609.06934
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen-2.5-7B, Qwen-2.5-7B-Instruct, Llama-3-8B and others15

    Abstract论文将后验安全脆弱性归因于正交抑制，并提出通过预训练持续共训练实现具备微调抗性的安全防护。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2608.20554

    aiXamine：跨维度评测 LLM 安全、安全（security）与隐私权衡

    提出 aiXamine 黑盒基准，统一评测 LLM 安全、稳健与隐私权衡

    arXiv
    2608.20554
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    openai/gpt-5-mini, openai/gpt-4o, anthropic/claude-haiku-4.5 and others15
    AbstractaiXamine 用九服务黑盒协议比较百余个模型，作者称单轴信任度进展可能削弱其他轴。

    aiXamine 是一套黑盒评测协议，用来在同一条件下比较 LLM 的 safety、security 与 privacy，而不是再产出一个能力分。

    Paper analysisRead analysis
You have reached the end