Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter4

Impact

Output manipulation3

Attack surface / entry point

User input26Web pages and interfaces17Documents and messages26Tool responses16Tool and skill descriptions5Code repositories and dependencies5Retrieval corpus26Memory writes8Inter-agent messages10Images, audio and video4Training data1Distribution channels9Inference services and hardware2

Layer

Model layer8Application layer3Training and data layer25
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Impact：Output manipulationAttack surface / entry point：Training dataAttack surface / entry point：Inference services and hardwareLayer：Application layerClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.02349

    MIRROR：面向多智能体通信的法定人数完整性防御

    提出 MIRROR，用多路径摘要多数表决保障多智能体通信完整性

    arXiv
    2610.02349
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Gemma-4-31B-it, Gemini 2.5 Pro
    AbstractMIRROR 靠多数路径。

    MIRROR 是 LLM 多智能体通信层上的多路径法定人数完整性原语，只处理不透明字节，不解释消息内容。要处理的是 Agent-in-the-Middle：中介合法终结 TLS 后可改在途消息，而语义校验有推理开销和误拦，签名又要求私钥管理。做法是生成结束后复制同一规范化载荷。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.17817

    论文：用投毒基准污染自改进编码 Agent，令其后续版本写出漏洞代码

    提出基准投毒攻击，使自修改编码 Agent 跨代写出含漏洞代码

    arXiv
    2609.17817
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.5, Qwen3.5-397B, gpt-oss-120b and others5

    Abstract论文报告了恶意基准能污染自修改代码智能体的进化过程并持续输出漏洞，警示系统设计需纳入安全约束。

    Paper analysisRead analysis
  3. 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