We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time. Our method can operate at any resolution and creates watermarks robust to a broad range of transformations (rotations, crops, JPEG, contrast, etc). It significantly outperforms the previous zero-bit methods, and its performance on multi-bit watermarking is on par with state-of-the-art encoder-decoder architectures trained end-to-end for watermarking. The code is available at github.com/facebookresearch/ssl_watermarking
@article{arxiv.2112.09581,
title = {Watermarking Images in Self-Supervised Latent Spaces},
author = {Pierre Fernandez and Alexandre Sablayrolles and Teddy Furon and Hervé Jégou and Matthijs Douze},
journal= {arXiv preprint arXiv:2112.09581},
year = {2022}
}