Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter2

Attack type

Jailbreaks4

Model risks

Dangerous agent actions3Inappropriate refusal4Hallucination and fabrication4

Impact

Harmful content4

System type

Models and APIs4

Attack surface / entry point

User input4
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.
Model risks：Inappropriate refusalAttack surface / entry point：User inputClear all

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

  1. DefensesarXiv 2610.13078

    Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs

    Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel

    arXiv
    2610.13078
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Qwen3-8B-Instruct and others18
    AbstractAttention updates are more readable for harmfulness, MLP updates write refusal, and Sentinel routes alerts using two-path signals.

    The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.

    Paper analysisRead analysis
  4. DefensesarXiv 2608.13304

    WIFA：按意图分组监督缓解包装式越狱与过度拒答

    提出 WIFA 意图组监督微调，缓解包装式越狱与过度拒答

    arXiv
    2608.13304
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct
    AbstractWIFA 用匹配意图组做数据层，WIFA-Boost 偏高安全，A-GCRT 在 Qwen 上把过拒降到基座以下。

    WIFA 是一种自动意图组数据构造，用来让安全微调拒绝有害意图而不是拒绝表面包装。WIFA-Boost 与 A-GCRT 在同一数据层上选取不同的安全–过拒工作点。

    Paper analysisRead analysis
You have reached the end