Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter5

Attack type

Poisoning and backdoors3

Defense type

Model hardening13Detection and filtering4Instruction–data separation2Permissions and approval1Monitoring and auditing3

System type

Models and APIs5

Attack surface / entry point

User input59Web pages and interfaces29Documents and messages25Tool responses47Tool and skill descriptions23Code repositories and dependencies6Retrieval corpus10Memory writes11Inter-agent messages8Images, audio and video15Training data7Weights and gradients3Distribution channels15Inference services and hardware3

Layer

Training and data layer3Infrastructure 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 filteringDefense type：Instruction–data separationDefense type：Permissions and approvalAttack 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.

  3. 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
  5. DefensesarXiv 2608.25431

    GIFT: Enforcing User Data Isolation in LLM Serving via GPU Information Flow Tracking

    Propose GIFT, isolating user data in shared LLM serving using encryption and GPU information flow tracking

    arXiv
    2608.25431
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-14B, Qwen2.5-32B, Qwen2.5-72B and others6
    AbstractGIFT uses cryptographic isolation plus GPU information flow rules to enforce user data isolation on vLLM and DistServe, and reports throughput overhead.

    GIFT is the authors' user data isolation system for shared LLM serving, with GIFT-CC enabling confidential computing. In the conclusion, the authors state it is the first IFT design for this scenario.

    Paper analysisRead analysis
  6. 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