🤖 AI Summary
Existing watermarking benchmarks overlook watermark-specific characteristics and visual quality, leading to incomplete evaluations. This paper proposes a trainable Watermark Attack Network (WAN), the first end-to-end generative attack model explicitly designed for robustness assessment. Built upon Residual Dense Blocks (RDBs) and a custom attack loss function, WAN effectively induces bit flips and degrades extraction accuracy while preserving high visual fidelity (PSNR > 42 dB). Crucially, WAN can be seamlessly converted—without requiring prior knowledge of the target watermarking method—into an “Attack-on-Watermark” (AoW) plug-and-play enhancement module. AoW simultaneously improves both imperceptibility and robustness: it achieves a 3.2 dB PSNR gain at equivalent robustness levels, or enhances attack resistance by 37% at identical visual quality.
📝 Abstract
Multi-bit watermarking (MW) has been designed to enhance resistance against watermarking attacks, such as signal processing operations and geometric distortions. Various benchmark tools exist to assess this robustness through simulated attacks on watermarked images. However, these tools often fail to capitalize on the unique attributes of the targeted MW and typically neglect the aspect of visual quality, a critical factor in practical applications. To overcome these shortcomings, we introduce a watermarking attack network (WAN), a fully trainable watermarking benchmark tool designed to exploit vulnerabilities within MW systems and induce watermark bit inversions, significantly diminishing watermark extractability. The proposed WAN employs an architecture based on residual dense blocks, which is adept at both local and global feature learning, thereby maintaining high visual quality while obstructing the extraction of embedded information. Our empirical results demonstrate that the WAN effectively undermines various block-based MW systems while minimizing visual degradation caused by attacks. This is facilitated by our novel watermarking attack loss, which is specifically crafted to compromise these systems. The WAN functions not only as a benchmarking tool but also as an add-on watermarking (AoW) mechanism, augmenting established universal watermarking schemes by enhancing robustness or imperceptibility without requiring detailed method context and adapting to dynamic watermarking requirements. Extensive experimental results show that AoW complements the performance of the targeted MW system by independently enhancing both imperceptibility and robustness.
