识别人脸伪造中多种编辑工具的联合使用，提升真实场景下的溯源能力。
Multi-Tool Image Editing Attribution in Facial Forgery
- 基于空间与频域特征，捕捉多工具留下的可区分痕迹。
- 在500万+图像数据集上实现五步内编辑的多工具准确识别。
- 适合需要高精度伪造溯源的数字取证与安全研究者。
随着生成式AI工具日益强大且易用，用户可通过提示词轻松编辑人脸图像，亟需图像编辑溯源技术来判断图像中涉及的具体编辑工具。现有方法多基于单工具假设，仅能识别单一编辑工具，难以应对日益普遍的多工具复合编辑场景——不同工具产生的痕迹相互叠加、干扰。为填补此空白，本文提出多工具图像编辑溯源（MIEA），旨在识别多工具编辑人脸图像中涉及的所有编辑工具。为此，构建了包含50万+张人脸图像的新数据集MultiEdit，覆盖六类支持人脸替换（Deepfake）和多种面部增强的编辑工具。基于数据分析发现，设计了DPEC方法，通过误差引导的课程学习策略，从空间与频域双重维度捕捉局部敏感的工具痕迹。实验表明，该方法在最多五步编辑的人脸图像上优于九种现有方法。
原文摘要 · Abstract (English)
As generative AI tools become increasingly powerful and easy to use, people can easily edit portrait images with a prompt, necessitating the task of image editing attribution, which predicts the involved editing tools from the given image. Existing attribution methods hold the single-tool assumption and can only attribute a specific editing tool, but struggle to handle the more complex and increasingly common multi-tool editing scenarios, where artifacts left by different editing tools are composite and overlapped. To address this gap, we explore Multi-Tool Image Editing Attribution (MIEA), which aims to identify multiple editing tools involved in a multi-tool edited facial image. To simulate the real-life editing operations on facial images, we then construct a new dataset, MultiEdit, which contains 500k+ edited facial images and covers six types of editing tools that support face swapping (Deepfake) and various facial enhancements. Inspired by the findings from data analysis, we design DPEC, a multi-tool attribution method that can capture distinguishable, locality-aware editing tool traces from both spatial and frequency domains with the support of an error-based curriculum learning strategy. Experiments show \Method\ outperforms nine methods for facial images edited in at most five steps.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。