Certified Neural Network Watermarks with Randomized Smoothing
Abstract
Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an adversary tries to copy the model. However, in practice, watermarks can often be removed by an intelligent adversary. Several papers have proposed watermarking methods that claim to be empirically resistant to different types of removal attacks, but these new techniques often fail in the face of new or better-tuned adversaries. In this paper, we propose a certifiable watermarking method. Using the randomized smoothing technique proposed in Chiang et al., we show that our watermark is guaranteed to be unremovable unless the model parameters are changed by more than a certain l2 threshold. In addition to being certifiable, our watermark is also empirically more robust compared to previous watermarking methods. Our experiments can be reproduced with code at https://github.com/arpitbansal297/Certified_Watermarks
Cite
@article{arxiv.2207.07972,
title = {Certified Neural Network Watermarks with Randomized Smoothing},
author = {Arpit Bansal and Ping-yeh Chiang and Michael Curry and Rajiv Jain and Curtis Wigington and Varun Manjunatha and John P Dickerson and Tom Goldstein},
journal= {arXiv preprint arXiv:2207.07972},
year = {2022}
}
Comments
ICML 2022