A0251
Title: A plug-and-play watermark framework for AI-generated images
Authors: Xuan Bi - University of Minnesota (United States) [presenting]
Abstract: Safeguarding intellectual property and preventing potential misuse of AI-generated images are of paramount importance. A robust and agile plug-and-play watermark detection framework, dubbed RAW, is introduced. As a departure from traditional encoder-decoder methods, which incorporate fixed binary codes as watermarks within latent representations, the approach introduces learnable watermarks directly into the original image data. Subsequently, a classifier is employed that is jointly trained with the watermark to detect the presence of the watermark. The proposed framework is compatible with various generative architectures and supports on-the-fly watermark injection after training. By incorporating state-of-the-art smoothing techniques, the framework provides provable guarantees regarding the false positive rate for misclassifying a watermarked image, even in the presence of certain adversarial attacks targeting watermark removal. Experiments on a diverse range of images generated by state-of-the-art diffusion models reveal substantial performance enhancements compared to existing approaches. For instance, the method demonstrates a notable increase in AUROC, from 0.48 to 0.82, when compared to state-of-the-art approaches in detecting watermarked images under adversarial attacks while maintaining image quality, as indicated by closely aligned FID and CLIP scores.
