Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter4

Attack type

Prompt injection3Poisoning and backdoors6

Defense type

Model hardening13Detection and filtering7Instruction–data separation7Permissions and approval9Monitoring and auditing4

Impact

Unauthorized actions3

System type

Models and APIs4AI Agent3

Attack surface / entry point

User input38Web pages and interfaces8Documents and messages10Tool responses16Tool and skill descriptions10Retrieval corpus5Memory writes3Inter-agent messages3Images, audio and video14Training data7Weights and gradients3Distribution channels8Inference services and hardware1

Layer

Application layer3Training and data layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Defense type：Detection and filteringAttack surface / entry point：Memory writesAttack surface / entry point：Weights and gradientsAttack surface / entry point：Inference services and hardwareClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.27124

    Fed-ADR：用恶意编排服务器协同客户端梯度操纵攻击联邦学习

    提出 Fed-ADR，用编排服务器协同操纵梯度攻破联邦学习并检测恢复

    arXiv
    2609.27124
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    CNN（MNIST：2 Conv + 3 FC）, CNN（Fashion-MNIST：6 Conv + 1 FC）, ResNet18（CIFAR-10）
    AbstractFed-ADR 用 gray-box 编排攻击绕过多种聚合防御，再用 Hessian 一致性检测和窗口内恢复把准确率拉回。

    Fed-ADR 是一套面向联邦学习的攻击、检测与恢复框架：编排服务器改写合谋客户端的梯度，使参数服务器的现有防御把投毒更新当成良性，同时在发现后用历史梯度把全局模型原地修回来。

    Paper analysisRead analysis
  7. DefensesarXiv 2608.02271

    Z-PEFT: Zero-shot backdoor detection for parameter-efficient fine-tuning based on canonical spectral features

    Propose Z-PEFT, which detects PEFT backdoors in a zero-shot manner using per-head spectral features.

    arXiv
    2608.02271
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Z-PEFT, Llama-2-7B, Llama-2-13B and others6
    Paper analysisRead analysis
You have reached the end