检测任意AI伪造文本图像
Detect Any AI-Counterfeited Text Image
DanceText 提供了覆盖全图生成、区域擦除与编辑三类伪造范式的十万级文本图像伪造数据集，并首次纳入多模态大模型与商用软件产物；DS-Net 的取证解耦编码器提取与生成器无关的伪影特征、协同去噪解码器联合图像级分类与实例级定位，可直接迁移到通用 AIGC 图像取证与篡改区域定位任务。
原文依据 a Forensic Decoupling Encoder to extract generator-agnostic artifact features
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成式AI的快速发展使得高度逼真的文本图像得以被创建，由此带来欺诈与虚假信息等重大安全风险。然而，现有数据集在规模、多样性以及伪造技术的时效性方面均存在不足，加之模型泛化能力欠佳，严重制约了鲁棒检测的研究。为弥补这些缺陷，我们提出DanceText，一个面向AI伪造文本图像检测的大规模、综合性数据集。该数据集借助我们新颖的Creative Proposer流水线构建，该流水线可自动化生成多样且逼真的伪造样本，使DanceText在多个维度上超越此前工作100倍以上。它首次纳入了来自多模态大模型、商业软件与移动应用的伪造样本，覆盖全图生成、区域移除与编辑等所有主要范式。基于该数据集，我们提出DS-Net，一种新颖且有效的检测模型。它包含两个关键组件：取证解耦编码器，用于提取与生成器无关的伪影特征；协同去噪解码器，将图像级分类与实例级定位协同起来。大量实验表明，DS-Net取得了最优性能，推动该领域朝着在真实场景中鲁棒且统一地检测AI伪造文本图像的方向发展。我们的代码与数据集都将公开发布。
英文原文摘要 1445 字符
The rapid advancement of generative AI enables the creation of highly realistic text images, posing significant security risks from fraud and disinformation. However, research into robust detection is critically hampered by existing datasets that lack scale, diversity, and updated counterfeit techniques, as well as by models that fail to generalize. To address these deficiencies, we introduce DanceText, a large-scale, comprehensive dataset for AI-counterfeited text image detection. Constructed using our novel Creative Proposer pipeline, which automates the generation of diverse and realistic counterfeits, DanceText surpasses previous works by over 100-fold in multiple dimensions. It is the first to include counterfeits from multimodal large models, commercial software, and mobile apps, covering all major paradigms, including full-image generation, regional removal, and editing. Building on this dataset, we propose DS-Net, a novel and effective detection model. It features two key components: a Forensic Decoupling Encoder to extract generator-agnostic artifact features, and a Synergy Denoising Decoder that synergizes image-level classification with instance-level localization. Extensive experiments demonstrate that DS-Net achieves state-of-the-art performance, advancing the field toward robust and unified detection of AI-counterfeited text images in real-world scenarios. Both our code and dataset will be released publicly.