# Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows?

arXiv: https://arxiv.org/abs/2605.27135 · HTML: https://mlsanity.com/paper/2605.27135/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 38 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 8 of 8)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses](https://mlsanity.com/paper/1811.09600/) (2018)
- [Video Seal: Open and Efficient Video Watermarking](https://mlsanity.com/paper/2412.09492/) (2024)
- [CGBA: Curvature-aware Geometric Black-box Attack](https://mlsanity.com/paper/2308.03163/) (2023)
- [Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models](https://mlsanity.com/paper/2510.20468/) (2025)
- [Geometric Image Synchronization with Deep Watermarking](https://mlsanity.com/paper/2509.15208/) (2025)

## Built on by (most cited first, 1 of 1)

- [Optimizing and Securing the Modern Watermarking Channel for Images](https://mlsanity.com/paper/2609.34744/) (2026)

## Abstract (arXiv)

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.