PromptForge-350k：一种大规模数据集和对比框架用于基于提示的AI图像伪造定位
PromptForge-350k: A Large-Scale Dataset and Contrastive Framework for Prompt-Based AI Image Forgery Localization
AI总结：
本文提出PromptForge-350k数据集和ICL-Net网络，通过自动化标注框架和对比学习提升伪造定位精度，实验显示在IoU指标上优于现有方法。
摘要：
基于提示的AI图像编辑技术的普及加剧了恶意内容生成的风险，但针对这些新兴编辑技术的伪造定位方法研究不足。本文首先提出一个全自动的掩码标注框架，利用关键点对齐和语义空间相似性生成精确的地面真实掩码。基于此框架，构建了覆盖四种先进提示式AI图像编辑模型的PromptForge-350k大规模伪造定位数据集，缓解该领域数据稀缺问题。此外，提出ICL-Net网络，包含三流主干和图像内对比学习，使模型能够捕捉高度鲁棒且可泛化的取证特征。大量实验表明，本文方法在PromptForge-350k上达到62.5%的IoU，优于现有方法5.1%。此外，其对常见退化具有强鲁棒性，IoU下降小于1%，并在未见编辑模型上表现出良好的泛化能力，平均IoU为41.5%。
英文摘要：
The rapid democratization of prompt-based AI image editing has recently exacerbated the risks associated with malicious content fabrication and misinformation. However, forgery localization methods targeting these emerging editing techniques remain significantly under-explored. To bridge this gap, we first introduce a fully automated mask annotating framework that leverages keypoint alignment and semantic space similarity to generate precise ground-truth masks for edited regions. Based on this framework, we construct PromptForge-350k, a large-scale forgery localization dataset covering four state-of-the-art prompt-based AI image editing models, thereby mitigating the data scarcity in this domain. Furthermore, we propose ICL-Net, an effective forgery localization network featuring a triple-stream backbone and intra-image contrastive learning. This design enables the model to capture highly robust and generalizable forensic features. Extensive experiments demonstrate that our method achieves an IoU of 62.5% on PromptForge-350k, outperforming SOTA methods by 5.1%. Additionally, it exhibits strong robustness against common degradations with an IoU drop of less than 1%, and shows promising generalization capabilities on unseen editing models, achieving an average IoU of 41.5%.
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。
