Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter1

Attack type

Poisoning and backdoors3

Defense type

Model hardening3

System type

Models and APIs5

Attack surface / entry point

User input85Web pages and interfaces18Documents and messages24Tool responses22Tool and skill descriptions12Code repositories and dependencies7Retrieval corpus7Memory writes11Inter-agent messages8Images, audio and video21Training data6Weights and gradients3Distribution channels8

Layer

Training and data layer5

System component

Fine-tuning and open weights3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 313papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Training dataClear all

Another 313papers do not have category tags yet and are not included in filtered results.

  3. Evaluation and benchmarksarXiv 2609.10952

    监督学习中的数据投毒攻击实证评估：标签翻转与后门投毒在 MNIST 和 Fashion-MNIST 上的对比

    比较标签翻转与后门投毒对图像分类器的影响

    arXiv
    2609.10952
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Logistic Regression, Linear SVM, Random Forest
    Abstract标签翻转更能拉低线性模型。

    Khan 与 Abusaqer 在两个图像分类基准上比较了两种训练时投毒。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2605.14605

    研究：恶意微调防御在持续训练下失效，72 条防御轨迹危害度全部上升

    用代价曲线评估恶意微调防御在持续训练下的衰减

    arXiv
    2605.14605
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat, Qwen3-8B, Llama-3.1-8B-Instruct and others8

    Abstract论文指出恶意微调防御在持续训练下均会衰减，表明基于有限攻击者假设的防御无法为开源模型提供持久保护。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2511.18921

    BackdoorVLM：面向视觉语言模型后门攻击与防御的基准

    提出 BackdoorVLM 基准，评测视觉语言模型微调中的后门攻击与防御

    arXiv
    2511.18921
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-1.5-7B, Qwen2.5-VL-7B
    AbstractBackdoorVLM 统一评测 VLM 后门与防御：含文本触发在低投毒率下更易激活，现有防御跨类型不稳定。

    BackdoorVLM 是作者提出的 VLM 后门攻击与防御评测基准，作者称它是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end