Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Attack type

Poisoning and backdoors3

Defense type

Model hardening3

Impact

Output manipulation3

System type

Models and APIs6LLM applications3AI Agent23coding agent3web agent3Multi-agent systems4

Attack surface / entry point

User input58Documents and messages1Images, audio and video16Training data5

Layer

Training and data layer5
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.
System type：Models and APIsAttack surface / entry point：Documents and messagesAttack surface / entry point：Training dataClear all

Another 232papers 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 2607.24177

    EXE-Bench：为真实可用性对 AI Windows 恶意软件检测器进行权衡排名

    提出 EXE-Bench 比较 Windows 恶意软件检测器的可用性权衡

    arXiv
    2607.24177
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    EmberGBDT, BBDnn, BBDnnFDRS and others15
    Abstract统一四指标后，手工特征的 EmberGBDT 综合居首，只看准确率会误导部署。

    EXE-Bench 用同一设置给 AI Windows 恶意软件检测器做四指标排序，而不是只比一次测试集准确率。。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2605.14605

    Study: malicious fine-tuning defenses fail under continued training, harmfulness rises across all 72 defense trajectories

    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
  6. 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