Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter3

System type

Models and APIs76LLM applications4AI Agent10coding agent3

Attack surface / entry point

User input30Web pages and interfaces7Documents and messages17Tool responses3Retrieval corpus23Images, audio and video7Weights and gradients1Inference services and hardware3
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.
System type：LLM applicationsAttack surface / entry point：Weights and gradientsAttack surface / entry point：Inference services and hardwareClear all

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

  1. AttacksarXiv 2610.09981

    研究：LLM 路由决策日志可推断用户医疗、自伤等敏感话题

    提出利用路由元数据推断敏感话题的侧信道攻击

    arXiv
    2610.09981
    Published
    Layer
    Infrastructure layer
    Setting
    LLM applications
    Evaluated models
    RouteLLM (BERT router), notdiamond-0001, Vela (vLLM Semantic Router)

    Abstract论文揭示并测量了 LLM 路由决策在无文本日志中的敏感话题泄露，验证了按类别公平性防御的有效性与边界。

    Paper analysisRead analysis
  3. AttacksarXiv 2604.03890

    从提示到物理动作：针对 LLM 中介机器人控制系统的结构化后门攻击

    提出结构化 JSON 后门，经投毒 LoRA 在机器人控制中触发恶意动作

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
  4. DefensesarXiv 2601.21189

    Adaptive robust cost-aware Proof of Quality for decentralized LLM inference networks

    为去中心化 LLM 推理网络提出稳健成本感知 PoQ，抵御恶意评估者操纵分数

    arXiv
    2601.21189
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    llama 3 2 3b, gemma 2 2b it, tinyllama 1 1b and others10
    Abstract成本感知 PoQ 加入稳健共识。

    这篇扩展工作把成本感知 Proof of Quality 的共识层改成能承受恶意评估分数的形式，奖励仍同时看输出质量与延迟成本。

    Paper analysisRead analysis
You have reached the end