Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter4

Attack type

Jailbreaks7Prompt injection4Extraction and theft1

System type

Models and APIs4

Attack surface / entry point

User input4

Layer

Model layer4Application layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Attack type：Prompt injectionAttack type：Extraction and theftLayer：Model layerLayer：Application layerClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. InterpretabilityarXiv 2610.12361

    Study: legal reasoning models citing legal provisions does not equal relying on legal provisions.

    Uses premise permutation and hidden-layer tracing to audit whether legal chain-of-thought truly relies on the cited legal provisions.

    arXiv
    2610.12361
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, Qwen3-14B, Llama-3.1-8B and others7
    AbstractUsing counterfactual substitution of authorities and internal commitment tracing, the authors find that legal CoT rulings depend on authorities only to a limited extent and are vulnerable to prompt injection manipulation.

    This study conducts an empirical audit of the causal truthfulness of legal citations in chain-of-thought reasoning of large language models in the legal domain.

    Paper analysisRead analysis
  2. InterpretabilityarXiv 2610.05295

    研究用因果追踪区分间接提示注入中的可读信号与有效干预

    用因果追踪区分间接提示注入中的角色可读性与有效干预

    arXiv
    2610.05295
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen-2.5-7B, Qwen-2.5-1.5B, Llama-3.1-8B and others8
    Abstract作者称源角色先于强工具选择效应可读，有效编辑还取决于位置、长度和方向来源。

    在权重固定的白盒模型上，源角色可以先被读出。沿相关方向的编辑是否改变行为，要在目标位点上另测。。

    Paper analysisRead analysis
  3. InterpretabilityarXiv 2609.37737

    研究用因果激活修补定位模型服从提示注入指令的决策层

    用因果激活修补定位模型服从提示注入的决策层

    arXiv
    2609.37737
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Qwen3-14B, Qwen3-32B and others7
    Abstract合规的因果杠杆集中在网络后三分之一的低秩子空间，该层也是混淆下检测最好的位置。

    这篇工作用逐层激活修补定位提示注入合规发生在网络何处，并把该位置用于检测验证。。

    Paper analysisRead analysis
  5. InterpretabilityarXiv 2609.11780

    用权重谱密度预测隐私泄露：WeightWatcher 谱指标可作为成员推理攻击脆弱性的代理

    检验权重谱度量能否代理成员推断泄漏

    arXiv
    2609.11780
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    MLP-1×4096, MLP-2×1024, MLP-2×2048 and others11
    Abstract作者认为谱度量与泛化差距互补，有望用于无数据的模型级筛查。

    作者在 MLP 上检查 WeightWatcher 谱统计是否与 online LiRA 同向，以便不看数据、不训练 shadow 模型就做模型级成员风险筛查。放出前的审计要知道训练成员会不会被认出来。LiRA 依赖大量 shadow 模型，候选一多就难以逐个跑。

    Paper analysisRead analysis
You have reached the end