StyleMark: A Robust Watermarking Method for Art Style Images Against Black-Box Arbitrary Style Transfer
Yunming Zhang, Dengpan Ye, Sipeng Shen, Jun Wang

TL;DR
StyleMark is a novel watermarking technique designed for art style images that remains robust against black-box arbitrary style transfer and various distortions, enabling precise attribution of artistic styles.
Contribution
It introduces a new style watermark network with multi-scale embedding and a distribution squeeze loss, effectively balancing robustness and invisibility in watermarking for style images.
Findings
StyleMark achieves high robustness against black-box AST.
It effectively defends against pixel-level distortions and adaptive attacks.
The method enables accurate attribution of artistic styles after style transfer.
Abstract
Arbitrary Style Transfer (AST) achieves the rendering of real natural images into the painting styles of arbitrary art style images, promoting art communication. However, misuse of unauthorized art style images for AST may infringe on artists' copyrights. One countermeasure is robust watermarking, which tracks image propagation by embedding copyright watermarks into carriers. Unfortunately, AST-generated images lose the structural and semantic information of the original style image, hindering end-to-end robust tracking by watermarks. To fill this gap, we propose StyleMark, the first robust watermarking method for black-box AST, which can be seamlessly applied to art style images achieving precise attribution of artistic styles after AST. Specifically, we propose a new style watermark network that adjusts the mean activations of style features through multi-scale watermark embedding,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Steganography and Watermarking Techniques · Digital Media Forensic Detection · Generative Adversarial Networks and Image Synthesis
MethodsFocus
