Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows?
For practitioners deploying watermarking in real-world scenarios, this work shows that classic methods may be more suitable than modern neural-network-based approaches.
The paper compares modern post-hoc watermarking methods with classic ones (e.g., Broken-Arrows) for AI-generated images, finding that classic methods outperform modern ones in security while maintaining robustness under realistic attacks.
With the rapid proliferation of generative models, such as diffusion models, digital watermarking has emerged as a crucial solution for identifying AI-generated images. Modern post-hoc watermarking schemes use neural networks to achieve an extremely low false-alarm rate while remaining robust to common image transformations. However, there is a lack of comparison between these modern methods and classic ones, particularly in real-world scenarios where robustness and security take precedence over achieving an extremely low false-alarm probability. In this paper, we propose a fair comparison of robustness and security between modern and classic post-hoc watermarking across various types of classic augmentations and recent sophisticated attacks. Our experiments show that, in a realistic scenario, classic watermarking outperforms modern techniques in terms of security while maintaining robustness.