Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter3

Attack type

Detection evasion8

Defense type

Watermarking and provenance7

System type

Models and APIs8

Attack surface / entry point

User input3Documents and messages8Images, audio and video9Weights and gradients3

Layer

Model layer8Application layer5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack type：Detection evasionAttack surface / entry point：Documents and messagesLayer：Model layerClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.11848

    SemField: training-free semantic watermark

    Proposes the semantic watermark SemField, which still identifies the attribution of generated text after paraphrasing and structural changes.

    arXiv
    2610.11848
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.2-1B, Qwen3-1.7B, OPT-1.3B
    AbstractTraining-independent document-level semantic watermark.

    SemField is a zero-bit semantic watermark embedded by the provider at generation time and detected later with a key, used to identify the provider's own model text after paraphrasing and sentence-level structural changes.

    Paper analysisRead analysis
  2. DefensesarXiv 2610.04763

    UT Austin 将 SynthID 水印嵌入基因组语言模型，凭 DNA 序列和密钥追溯 AI 生成片段

    把 SynthID 嵌入基因组语言模型采样，并用位置无关检测追溯生成序列

    arXiv
    2610.04763
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Carbon-500M, GENERator-v2-eukaryote-1.2b-base
    Abstract两个六碱基基因组模型嵌入 SynthID 后，位置无关验证能找回水印，作者称这只是统计检测。

    作者在两个六碱基基因组模型的采样里嵌入 SynthID，并让验证者在不知道起点、链和 token phase 时做一次校正后的检出。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.37310

    AutoMark：让自动研究流程自主发现更优 LLM 水印方案

    提出 AutoMark，自动搜索并统计检验 LLM 文本水印

    arXiv
    2609.37310
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen3.8-27B, GPT-6 Astra and others5
    AbstractAutoMark 的贡献同时包含搜索出的水印，以及用于约束自动研究误报与评测漏洞的验证框架。

    AutoMark 是一套自动水印研究框架：先检查生成分布和误报性质，再比较检测、编辑鲁棒性与质量，最后人工分析组件并做留出评测。

    Paper analysisRead analysis
  5. DefensesarXiv 2609.36372

    TTMark：超越单 token 熵的成对无失真水印

    提出成对无失真水印 TTMARK，增强低熵下的机器文本检测

    arXiv
    2609.36372
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama3.2-3B-Instruct, Mistral-v0.3-7B-Instruct, Qwen2.5-7B-Instruct
    AbstractTTMARK 用水印化相邻 token 对利用条件熵，在多种无失真方案上提高检测并保持生成质量。

    TTMARK 是一种成对、无失真的文本水印：对相邻 token 的联合分布重加权，而不是逐 token 独立重加权。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.14257

    DenMark：面向扩散语言模型的鲁棒语义水印

    提出 DenMark，在扩散语言模型去噪时注入可抵抗保义编辑的语义水印

    arXiv
    2609.14257
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaDA-8B, LLaDA1.5-8B, LLaDA2.0-mini and others4
    AbstractDenMark 用 rollout 在 DLM 去噪中累积语义水印，扫描检测以抵抗保义编辑。

    DenMark 是面向扩散语言模型的语义水印：在去噪的局部更新里注入密钥相关语义信号，并在编辑改变 token 边界后仍检测。现有句子级语义水印要先完成整个语义单元再打分取舍，而 DLM 以任意顺序更新掩码，中间单元不完整。DenMark 把续写划成固定 token 区域，对每个局部候选做不提交的 rollout 补全，按语义分 gb 的平均选择更新，从而沿轨迹累积证据。

    Paper analysisRead analysis
  8. 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
You have reached the end