AnchMark: Anchor-contrastive Watermarking vs GenAI-based Image Modifications

Minzhou Pan, Yi Zeng, Xue Lin, Ning Yu, Cho-Jui Hsieh, Ruoxi Jia

Keywords: Digital Watermark, Image Watermark, Diffusion Model Watermark, Diffusion Model

Abstract: This work explores the evolution of watermarking techniques designed to preserve the integrity of digital image content, especially against perturbations encountered during image transmission. An overlooked vulnerability is unveiled: existing watermarks' detectability significantly drops against even moderate generative model modifications, prompting a deeper investigation into the societal implications from a policy viewpoint. In response, we propose ANCHMARK, a robust watermarking paradigm, which remarkably achieves a detection AUC exceeding 0.93 against perturbations from unseen generative models, showcasing a promising advancement in reliable watermarking amidst evolving image modification techniques.

Submission Number: 54