ScreenMark: Watermarking Arbitrary Visual Content on Screen

TL;DR

ScreenMark is a novel watermarking method tailored for protecting dynamic and multi-modal visual screen content against theft via screenshots, demonstrating high robustness and imperceptibility in extensive tests.

Contribution

The paper introduces ScreenMark, a three-stage progressive watermarking framework specifically designed for arbitrary visual screen content protection, addressing limitations of existing media-specific methods.

Findings

High robustness against real-world screenshot attacks

Imperceptible watermark embedding in diverse screen content

Validated effectiveness on a large dataset of 100,000 screenshots

Abstract

Digital watermarking has shown its effectiveness in protecting multimedia content. However, existing watermarking is predominantly tailored for specific media types, rendering them less effective for the protection of content displayed on computer screens, which is often multi-modal and dynamic. Visual Screen Content (VSC), is particularly susceptible to theft and leakage through screenshots, a vulnerability that current watermarking methods fail to adequately address.To address these challenges, we propose ScreenMark, a robust and practical watermarking method designed specifically for arbitrary VSC protection. ScreenMark utilizes a three-stage progressive watermarking framework. Initially, inspired by diffusion principles, we initialize the mutual transformation between regular watermark information and irregular watermark patterns. Subsequently, these patterns are integrated with screen content using a pre-multiplication alpha blending technique, supported by a pre-trained screen decoder for accurate watermark retrieval. The progressively complex distorter enhances the robustness of the watermark in real-world screenshot scenarios. Finally, the model undergoes fine-tuning guided by a joint-level distorter to ensure optimal performance. To validate the effectiveness of ScreenMark, we compiled a dataset comprising 100,000 screenshots from various devices and resolutions. Extensive experiments on different datasets confirm the superior robustness, imperceptibility, and practical applicability of the method.