Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter4

Attack type

Poisoning and backdoors4

Defense type

Model hardening3

System type

Models and APIs5LLM applications4AI Agent16coding agent1web agent8Browser and computer use3

Attack surface / entry point

User input65Web pages and interfaces1Documents and messages4Tool responses3Tool and skill descriptions4Code repositories and dependencies7Memory writes3Images, audio and video17Training data5Weights and gradients3Distribution channels5

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 248papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Training dataClear all

Another 248papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2609.28915

    研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

    构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性

    arXiv
    2609.28915
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    AdaBoost, XGBoost, TabPFN and others10
    AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。

    ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。

    Paper analysisRead analysis
  4. 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
  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