Abstract:
Multi-bit watermarking (MW) has been developed to improve robustness against signal processing operations and geometric distortions. To this end, benchmark tools that test robustness by applying simulated attacks on watermarked images are available. However, limitations in these general attacks exist since they cannot exploit specific characteristics of the targeted MW. In addition, these attacks are usually devised without consideration of visual quality, which rarely occurs in the real world. To address these limitations, we propose a watermarking attack network (WAN), a fully trainable watermarking benchmark tool that utilizes the weak points of the target MW and induces an inversion of the watermark bit, thereby considerably reducing the watermark extractability. To hinder the extraction of hidden information while ensuring high visual quality, we utilize a residual dense blocks-based architecture specialized in local and global feature learning. A novel watermarking attack loss is introduced to break the MW systems. We empirically demonstrate that the WAN can successfully fool various block-based MW systems. Moreover, we show that existing MW methods can be improved with the help of the WAN as an add-on module.
