Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter5

Attack type

Prompt injection4Poisoning and backdoors4Model tampering2

Attack technique

Gradient and representation optimization2

Attack surface / entry point

Web pages and interfaces0Training data1Weights and gradients8Inference services and hardware1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Attack type：Model tamperingAttack technique：Gradient and representation optimizationAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Training dataAttack surface / entry point：Inference services and hardwareClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.05894

    研究者提出闭环偏见注入攻击

    提出闭环激活引导，在扩散语言模型去噪过程中注入定向偏见

    arXiv
    2610.05894
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    LLaDA-8B-Instruct, Dream-v0-Instruct-7B, LLaDA-MoE-7B-A1B-Instruct

    Abstract通过去噪中间概率反馈动态调节残差流转向，证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.39788

    研究：多智能体系统潜在通信链路可被训练用于提升有害顺从

    提出只训练或篡改多智能体潜在通信链路来提高有害遵从

    arXiv
    2609.39788
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
    Abstract潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。

    学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。

    Paper analysisRead analysis
You have reached the end