Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Defense type

Model hardening5Inference-time intervention4Detection and filtering33Instruction–data separation16Permissions and approval18Monitoring and auditing16

System type

Models and APIs39LLM applications3AI Agent10coding agent1web agent0Embodied systems and robotics3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Defense type：Inference-time interventionSystem type：LLM applicationsSystem type：coding agentSystem type：web agentClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2610.04860

    Research reveals that text watermarks induce model hallucinations and proposes two mitigation interventions

    分析文本水印在 RAG 中诱发事实幻觉的机制并提出干预

    arXiv
    2610.04860
    Published
    Layer
    Model layer
    Setting
    LLM applications
    Evaluated models
    LLaMA 3.1 8B Instruct, Mistral-7B-Instruct-v0.3, Qwen2.5-14B-Instruct
    Abstract论文揭示了生产环境文本水印导致模型事实退化的失效模式，分析了解码机制并提出针对性干预。

    论文研究生产级文本水印对大语言模型事实准确性的影响，分析了水印诱发幻觉的失效模式并评估了针对性缓解方案。

    Paper analysisRead analysis
  2. InterpretabilityarXiv 2609.08173

    基于 SAE 引导的关键路径识别（KPI）解决知识冲突

    提出 KPI，用入度定位跨层关键路径并做 SAE 转向以解决知识冲突

    arXiv
    2609.08173
    Published
    Layer
    Model layer
    Setting
    LLM applications
    Evaluated models
    Llama-3-8B, Llama-3.1-8B, Gemma-2-9B
    AbstractKPI 以入度关键路径替代大批 SAE 特征转向，在冲突 RAG 上提高忠实并减轻副作用。

    KPI 针对知识冲突 RAG 中的 SAE 转向：相关性批量改特征会带入冗余，少量因果上关键的特征即可完成转向。

    Paper analysisRead analysis
  3. DefensesarXiv 2606.22673

    Agent MechSuits：面向多轮 CLI Agent 的机制子空间安全引导

    提出 Agent MechSuits，对多轮 CLI Agent 做步级检测与子空间转向

    arXiv
    2606.22673
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    LLaMA-3.1-8B, Qwen-2.5-7B, Gemma-2-9B
    Abstract白盒步级探针加稀疏转向可压低三模型恶意动作，同时提高生成崩溃率。

    Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御，并配有可执行轨迹基准 MAS。

    Paper analysisRead analysis
  4. DefensesarXiv 2606.18673

    Understanding and mitigating prompt leakage attacks in real-world LLM applications

    Propose soft prompt defense AREA, re-anchoring attention to mitigate system prompt leakage

    arXiv
    2606.18673
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    Llama-2-7B-chat-hf, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others8
    AbstractThe authors measure commercial prompt leakage, propose attention drift, and use AREA to strike a trade-off between usability and leakage resistance.

    The authors study system prompt leakage in real LLM applications and propose AREA, a mitigation method that does not modify weights.

    Paper analysisRead analysis
You have reached the end