Universal Adversarial Watermarking for Text Image Protection via Template-Based Underpainting

Text images are images that contain textual content. They are vulnerable to content piracy through Optical Character Recognition (OCR) and unauthorized distribution. Existing methods based solely on adversarial examples or digital watermarking are insufficient to address both threats effectively. In this work, we propose Universal Adversarial Watermarking (UAW), a dual protection that misleads OCR systems and enables watermarking for traceability simultaneously. Specifically, we first generate two templates for representing watermark bits while attaining adversarial capability against OCR. Then, the watermark message is encoded via structured tiling of the bit templates into the underpainting of text images. Finally, the embedded watermark can be reliably extracted with the aid of watermark block synchronization and a majority voting mechanism. Experimental results demonstrate the effectiveness of the proposed method in terms of adversarial capability and watermarking functionality. We also validate the transferability of UAW across various font sizes, colors and languages, and evaluate the practical usage through real-world applications. The code is publicly available athttps://github.com/yfjn/UAW.