Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

TL;DR

This paper introduces W-Bench, a comprehensive benchmark for evaluating watermarking robustness against advanced image editing, and proposes VINE, a new method that significantly improves watermark robustness and imperceptibility using frequency analysis and a pretrained diffusion model.

Contribution

The paper presents W-Bench for benchmarking watermarking robustness and introduces VINE, a novel watermarking technique leveraging frequency analysis and diffusion models for enhanced robustness.

Findings

Most existing watermarking methods fail after advanced image edits.

VINE significantly outperforms existing methods in robustness and image quality.

Using surrogate attacks based on blurring improves watermark robustness during training.

Abstract

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright protection. In this work, we introduce W-Bench, the first comprehensive benchmark designed to evaluate the robustness of watermarking methods against a wide range of image editing techniques, including image regeneration, global editing, local editing, and image-to-video generation. Through extensive evaluations of eleven representative watermarking methods against prevalent editing techniques, we demonstrate that most methods fail to detect watermarks after such edits. To address this limitation, we propose VINE, a watermarking method that significantly enhances robustness against various image editing techniques while maintaining high image quality. Our approach involves two key innovations: (1) we analyze the frequency characteristics of image editing and identify that blurring distortions exhibit similar frequency properties, which allows us to use them as surrogate attacks during training to bolster watermark robustness; (2) we leverage a large-scale pretrained diffusion model SDXL-Turbo, adapting it for the watermarking task to achieve more imperceptible and robust watermark embedding. Experimental results show that our method achieves outstanding watermarking performance under various image editing techniques, outperforming existing methods in both image quality and robustness. Code is available at https://github.com/Shilin-LU/VINE.