On the Robustness of Backdoor-based Watermarking in Deep Neural Networks
Masoumeh Shafieinejad, Nils Lukas, Jiaqi Wang, Xinda Li, Florian Kerschbaum
Abstract
Watermarking algorithms have been introduced in the past years to protect deep learning models against unauthorized re-distribution. We investigate the robustness and reliability of state-of-the-art deep neural network watermarking schemes. We focus on backdoor-based watermarking and propose two simple yet effective attacks -- a black-box and a white-box -- that remove these watermarks without any labeled data from the ground truth. Our black-box attack steals the model and removes the watermark with only API access to the labels. Our white-box attack proposes an efficient watermark removal when the parameters of the marked model are accessible, and improves the time to steal a model up to twenty times over the time to train a model from scratch. We conclude that these watermarking algorithms are insufficient to defend against redistribution by a motivated attacker.