TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding

arXiv:2202.06091v3 Announce Type: replace
Abstract: Watermarking of deep neural networks (DNNs) has gained significant traction in recent years, with numerous (watermarking) strategies being proposed as mechanisms that can help verify the ownership of a DNN in scenarios where these models are obtained without the permission of the owner. However, a growing body of work has demonstrated that existing watermarking mechanisms are highly susceptible to removal techniques, such as fine-tuning, parameter pruning, or shuffling. In this paper, we build upon extensive …

arxiv can channel coding cs.cr cs.it cs.lg math.it mechanisms network networks neural network neural networks ownership permission spectrum strategies verify watermarking