UWPD: A General Paradigm for Invisible Watermark Detection Agnostic to Embedding Algorithms

TL;DR

This work proposes a novel task named Universal Watermark Presence Detection (UWPD), which aims to identify whether an image carries a copyright mark without requiring decoding information, and proposes the Frequency Shield Network (FSNet), a model that exhibits superior zero-shot detection capabilities on the UWPD task, outperforming existing baseline models.

Abstract

Invisible watermarks, as an essential technology for image copyright protection, have been widely deployed with the rapid development of social media and AIGC. However, existing invisible watermark detection heavily relies on prior knowledge of specific algorithms, leading to limited detection capabilities for "unknown watermarks" in open environments. To this end, we propose a novel task named Universal Watermark Presence Detection (UWPD), which aims to identify whether an image carries a copyright mark without requiring decoding information. We construct the UniFreq-100K dataset, comprising large-scale samples across various invisible watermark embedding algorithms. Furthermore, we propose the Frequency Shield Network (FSNet). This model deploys an Adaptive Spectral Perception Module (ASPM) in the shallow layers, utilizing learnable frequency gating to dynamically amplify high-frequency watermark signals while suppressing low-frequency semantics. In the deep layers, the network introduces Dynamic Multi-Spectral Attention (DMSA) combined with tri-stream extremum pooling to deeply mine watermark energy anomalies, forcing the model to precisely focus on sensitive frequency bands. Extensive experiments demonstrate that FSNet exhibits superior zero-shot detection capabilities on the UWPD task, outperforming existing baseline models. Code and datasets will be released upon acceptance.

Figures (7)

• Figure 1: Background and motivation of the UWPD task showing the challenges of universal watermark detection.
• Figure 2: Overview of the Frequency Shield Network (FSNet) architecture showing the Adaptive Spectral Perception Module (ASPM) and Dynamic Multi-Spectral Attention (DMSA).
• Figure 3: Model performance on different dataset ratios (10% to 100%). The accuracy increases with dataset size but shows diminishing returns after 30-50%.
• Figure 4: Performance comparison after completely removing similar watermark algorithms from the dataset. Base represents the performance without removal, and Amb. represents the performance after removal.
• Figure 5: Visualization of absolute residual extremum binarization triggered by four watermarking algorithms under a pure white background. From left to right: Dense periodic vertical stripes of LSB; extremely sparse impulse dot matrix of Patchwork; continuous and dense high-frequency grid perturbations of DCT and DWT.