Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter5

Attack type

Poisoning and backdoors3

Impact

Harmful content220Unauthorized actions11Data and privacy leaks52Output manipulation46Availability and reliability7Oversight failure12Increased misuse capability3

System type

Models and APIs7AI Agent4coding agent0

Attack surface / entry point

User input4Training data6Weights and gradients3

Layer

Prompt layer3Training and data layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilitySystem type：Models and APIsSystem type：coding agentAttack surface / entry point：User inputAttack surface / entry point：Weights and gradientsClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.10276

    PatchBench 提出激活补丁局部评测协议，揭示越狱修复的附带损伤

    提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤

    arXiv
    2610.10276
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8

    Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。

    Paper analysisRead analysis
  2. AttacksarXiv 2610.09819

    FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵

    提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门

    arXiv
    2610.09819
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    HuBERT-base, WavLM-base

    Abstract论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。

    Paper analysisRead analysis
  3. AttacksarXiv 2609.29948

    ENDOPROMPT：用受害者侧伪参考学习降低模型任务效用的前缀

    提出 ENDOPROMPT，以受害者侧伪参考学习降低良性任务效用的前缀

    arXiv
    2609.29948
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B, Llama-3.1-8B, Mistral-7B-v0.3 and others4
    Abstract作者用受害模型续写监督良性效用攻击，并把行为位移、任务退化与请求匹配效果分开评测。

    ENDOPROMPT 是一种用受害模型自身续写监督前缀生成的 white-box 效用攻击方法。它针对良性任务失败，不要求产生有害内容或明确拒答。

    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
  5. 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. AttacksarXiv 2605.13338

    研究者提出层级遗传算法黑盒攻击，诱导推理模型过度思考

    提出层级遗传算法 HGA，扰动题目逻辑结构诱发推理模型过度思考

    arXiv
    2605.13338
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    DeepSeek-R1 (671B), Qwen3-Thinking, GPT-o3 and others5

    AbstractHGA 在黑盒推理模型上用逻辑扰动拉长输出，作者称可从小代理迁移，查询成本是其局限。

    Paper analysisRead analysis
You have reached the end