On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark
Abstract
This work investigates the theoretical boundaries of creating publicly-detectable schemes to enable the provenance of watermarked imagery. Metadata-based approaches like C2PA provide unforgeability and public-detectability. ML techniques offer robust retrieval and watermarking. However, no existing scheme combines robustness, unforgeability, and public-detectability. In this work, we formally define such a scheme and establish its existence. Although theoretically possible, we find that at present, it is intractable to build certain components of our scheme without a leap in deep learning capabilities. We analyze these limitations and propose research directions that need to be addressed before we can practically realize robust and publicly-verifiable provenance.
Cite
Text
Fairoze et al. "On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.Markdown
[Fairoze et al. "On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark." Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, 2025.](https://mlanthology.org/aistats/2025/fairoze2025aistats-difficulty/)BibTeX
@inproceedings{fairoze2025aistats-difficulty,
title = {{On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark}},
author = {Fairoze, Jaiden and Ortiz-Jimenez, Guillermo and Vecerik, Mel and Jha, Somesh and Gowal, Sven},
booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics},
year = {2025},
pages = {1891-1899},
volume = {258},
url = {https://mlanthology.org/aistats/2025/fairoze2025aistats-difficulty/}
}