Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter5

Attack type

Poisoning and backdoors6

Impact

Harmful content20Unauthorized actions24Data and privacy leaks14Output manipulation34Availability and reliability7

System type

Models and APIs5

Attack surface / entry point

User input3Web pages and interfaces3Tool and skill descriptions3Memory writes1Training data6Weights and gradients3Distribution channels4

Layer

Application layer1Training and data layer6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilityAttack surface / entry point：Memory writesAttack surface / entry point：Training dataLayer：Application layerLayer：Training and data layerClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2609.32288

    预训练数据投毒的可解理论：依赖极限顺序的缩放指数

    证明预训练投毒的清洁超额风险指数随极限顺序变化

    arXiv
    2609.32288
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    OLMo-style models
    Abstract投毒清洁超额风险的幂指数取决于先固定宽高比还是先取充足数据极限。

    可解的预训练数据投毒理论：清洁超额风险的缩放指数随极限顺序改变。。

    Paper analysisRead analysis
  2. 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. AttacksarXiv 2609.22711

    UBA-ORL：针对离线强化学习的遗忘激活后门攻击

    提出 UBA-ORL，以 BD/CM 样本在遗忘后激活离线 RL 后门

    arXiv
    2609.22711
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    TD3+BC, BCQ, IQL
    AbstractUBA-ORL 用竞争的 BD/CM 样本，使离线 RL 后门在删除伪装轨迹后激活。

    UBA-ORL 研究离线强化学习中由合规轨迹删除激活的后门：合法贡献者同时上传共享触发的后门轨迹和伪装轨迹，训练后触发响应被压低，删除伪装批次后再升高。受害系统是使用静态数据集和轨迹级遗忘接口的离线 RL 服务。对手不能看到训练算法、参数、梯度或具体遗忘算法，但能提交可区分批次，并在部署时向观测注入预定触发。

    Paper analysisRead analysis
  6. AttacksarXiv 2609.01495

    去中心化联邦学习中的拜占庭节点放置优化

    提出 BPI 选点算法，增强去中心化联邦学习中的模型与数据投毒

    arXiv
    2609.01495
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    AbstractBPI 用有限轮 gossip 暴露选拜占庭集合。

    作者把 DFL 中“破坏哪 m 个节点”写成攻击者在固定预算下的优化问题，并用 BPI 近似有限轮内诚实节点受到的拜占庭暴露。

    Paper analysisRead analysis
  7. DefensesarXiv 2601.03401

    Using LLM alignment mechanisms to make data unlearnable

    提出 Disclaimer Injection，利用对齐机制使文本难以被学习

    arXiv
    2601.03401
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA-3-8B-Instruct
    Abstract黑盒声明注入压低微调分数，作者把它归因于对齐层持续激活。

    作者提出数据级方法 Disclaimer Injection，在 black-box 条件下降低文本被当代 LLM 微调学会的程度。所有者公开文本时未必打算供人训练。作者认为抓取之后法律手段难起作用，而早期模型上的表层扰动要么被当代 LLM 恢复语义，要么损坏可读性。

    Paper analysisRead analysis
You have reached the end