StyleMark: Robust Style Watermarking for Artworks Against Black-Box Zero-Shot Style Transfer
Yunming Zhang, Dengpan Ye, Sipeng Shen, Jun Wang, Caiyun Xie · IEEE Transactions on Information Forensics and Security · 2025
Zero-shot style transfer(ZSST) enables the rendering of real-world natural images into the painting styles of arbitrary artworks without requiring fine-tuning on unseen artistic styles. This low-cost and efficient approach to artistic recreation promotes the dissemination and communication of art. However, misuse of unauthorized artistic style images for ZSST may infringe on the copyrights of artists. One countermeasure is robust watermarking, which tracks image propagation by embedding copyright watermarks into carriers. Unfortunately, the stylized image generated by ZSST 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 ZSST, which can be seamlessly applied to artistic style images achieving precise attribution of artistic styles after ZSST, without compromising the social usability of artworks. Specifically, we propose a new style watermark network that adjusts the mean activations of style features through multi-scale watermark embedding, thereby planting watermark traces into the shared style feature space of style images. Furthermore, we design a distribution squeeze loss, which constrain content statistical feature distortion, forcing the reconstruction network to focus on integrating style features with watermarks, thus optimizing the intrinsic watermark distribution. Finally, based on solid end-to-end training, StyleMark mitigates the optimization conflict between robustness and watermark invisibility through decoder fine-tuning under random noise. Experimental results demonstrate that StyleMark exhibits significant robustness against black-box ZSST and common pixel-level distortions, maintains high watermark decoding accuracy under complex multi-stage processing scenarios, and securely defending against malicious adaptive attacks.