Poster
in
Workshop: Regulatable ML: Towards Bridging the Gaps between Machine Learning Research and Regulations
AnchMark: Anchor-contrastive Watermarking vs GenAI-based Image Modifications
Minzhou Pan · Yi Zeng · Xue Lin · Ning Yu · Cho-Jui Hsieh · Ruoxi Jia
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.
Chat is not available.