Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data

arXiv:2403.10663v1 Announce Type: cross
Abstract: With the increasing prevalence of Machine Learning as a Service (MLaaS) platforms, there is a growing focus on deep neural network (DNN) watermarking techniques. These methods are used to facilitate the verification of ownership for a target DNN model to protect intellectual property. One of the most widely employed watermarking techniques involves embedding a trigger set into the source model. Unfortunately, existing methodologies based on trigger sets are still susceptible to functionality-stealing attacks, potentially enabling …

abstract arxiv change cs.cr cs.cv cs.lg data deep neural network dnn features focus labels learn machine machine learning network networks neural network neural networks ownership platforms service type verification view watermarking