Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack type

Jailbreaks35Prompt injection5Poisoning and backdoors7Model tampering3Extraction and theft21Detection evasion3Malicious use4

System type

Models and APIs3

Attack surface / entry point

User input3Web pages and interfaces0Documents and messages8Images, audio and video9Training data1Weights and gradients3

Layer

Prompt layer15Model layer3Application layer11
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Attack type：Detection evasionAttack surface / entry point：User inputAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Training dataLayer：Model layerClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2604.10893

    研究者提出 Adaptive Stealing 自适应窃取水印攻击方法

    提出 Adaptive Stealing，自适应窃取印章以擦除或伪造水印

    arXiv
    2604.10893
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    OPT-2.7b, Llama3-8b
    AbstractAS 用逐步选印章做水印伪造与擦除，作者称其攻击效果高于固定策略的 WS。

    AS 是一种窃取生成式 LLM 水印的算法，用来在密钥和检测接口不可用时伪造或擦除水印。

    Paper analysisRead analysis
  3. AttacksarXiv 2510.10987

    DITTO：通过知识蒸馏伪造水印 LLM 的作者归属

    提出 DITTO 框架，蒸馏提取水印信号并注入外部模型以伪造归属

    arXiv
    2510.10987
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Llama3.1-8B, Llama3.2-3B, GPT-OSS 20B and others4

    Abstract论文针对大模型水印归属假设的脆弱性，提出黑盒仿冒攻击 DITTO，实现跨架构和采样方案的高检测率与低困惑度仿冒。

    Paper analysisRead analysis
You have reached the end