模型溯源归属：跨生成模型追踪多阶段操纵
Modelship Attribution: Tracing Multi-Stage Manipulations Across Generative Models
AI总结：
本文首次提出“Modelship Attribution”任务，用于追踪图像在多生成模型迭代操纵中的模型序列与编辑演化，并构建 MAT 框架及首个含 83,700 张图像的数据集，有效解决了多阶段操纵溯源问题。
摘要：
随着生成技术变得越来越易于获取，真实视觉内容经常被不同个体使用各种工具进行反复修改。目前，为了避免错误信息并确保问责，大量关于检测与溯源归属的研究正在涌现。尽管这些方法在单阶段操纵场景中显示出潜力，但在应对复杂的现实世界迭代操纵时仍存在不足。在本文中，据我们所知，我们首次系统地对这一现实世界挑战进行建模，并提出了一种新颖的方法来解决它。我们定义了一个名为“Modelship Attribution”的任务，旨在通过识别所涉及的生成模型并重建它们执行的编辑序列来追踪被操纵图像的演变过程。为了真实地模拟这一场景，我们使用了三种生成模型，即 StyleMapGAN、DiffSwap 和 FacePartsSwap，它们依次修改同一图像的不同区域。这一过程促成了首个 modelship 数据集的创建，该数据集包含 83,700 张图像（16,740 张图像×5）。鉴于后续编辑往往会覆盖早期模型的指纹，重点从提取混合指纹转向刻画每个模型独特的编辑模式。为了应对这一挑战，我们提出了 modelship attribution transformer（MAT），这是一个专门构建的框架，旨在有效识别和归属复杂多阶段操纵工作流中各种模型的贡献。通过大量实验以及与其他相关方法的比较分析，我们的结果（包括全面的消融研究）表明，所提出的方法是解决 modelship attribution 问题的一种高效方案。
英文摘要：
As generative techniques become increasingly accessible, authentic visuals are frequently subjected to iterative alterations by various individuals employing a variety of tools. Currently, to avoid misinformation and ensure accountability, a lot of research on detection and attribution is emerging. Although these methods demonstrate promise in single-stage manipulation scenarios, they fall short when addressing complex real-world iterative manipulation. In this paper, we are the first, to the best of our knowledge, to systematically model this real-world challenge and introduce a novel method to solve it. We define a task called "Modelship Attribution", which aims to trace the evolution of manipulated images by identifying the generative models involved and reconstructing the sequence of edits they performed. To realistically simulate this scenario, we utilize three generative models, StyleMapGAN, DiffSwap, and FacePartsSwap, that sequentially modify distinct regions of the same image. This process leads to the creation of the first modelship dataset, comprising 83,700 images (16,740 images*5). Given that later edits often overwrite the fingerprints of earlier models, the focus shifts from extracting blended fingerprints to characterizing each model's distinctive editing patterns. To tackle this challenge, we introduce the modelship attribution transformer (MAT), a purpose-built framework designed to effectively recognize and attribute the contributions of various models within complex, multi-stage manipulation workflows. Through extensive experiments and comparative analysis with other related methods, our results, including comprehensive ablation studies, demonstrate that the proposed approach is a highly effective solution for modelship attribution.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
