Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter6

Attack type

Jailbreaks3Prompt injection10Poisoning and backdoors4Extraction and theft8Detection evasion10

System type

Models and APIs3coding agent0web agent0

Attack surface / entry point

User input213Documents and messages1Tool responses4Images, audio and video48Weights and gradients7Inference services and hardware2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksSystem type：Models and APIsSystem type：coding agentSystem type：web agentAttack surface / entry point：Documents and messagesAttack surface / entry point：Inference services and hardwareClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2606.11817

    研究：语法约束解码可越狱 LLM 生成恶意代码，并提出 CodeShield 防御

    提出 CodeSpear 越狱，借语法约束解码生成恶意代码，并给出 CodeShield 防御

    arXiv
    2606.11817
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen2.5-Coder-7B, Qwen2.5-Coder-32B, Qwen2.5-7B and others10

    Abstract论文发现语法约束解码会破坏自然语言安全对齐，提出 CodeSpear 越狱攻击与基于蜜罐代码对齐的 CodeShield 防御。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2602.14161

    When benchmarks lie: evaluating malicious prompt classifiers under real-world distribution shift

    提出 LODO 评测恶意提示探针的跨数据集泛化

    arXiv
    2602.14161
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-3-27B, Qwen-3.5-4B and others5
    Abstract作者称 LODO 露出 CV 高估，数据集身份与安全方向部分重叠，标准域泛化干预关不上。

    LODO 用来检查恶意提示词分类器换成没见过的数据集后，还剩多少检测能力。。

    Paper analysisRead analysis
You have reached the end