DNNShield: Embedding Identifiers for Deep Neural Network Ownership Verification

arXiv:2403.06581v1 Announce Type: new
Abstract: The surge in popularity of machine learning (ML) has driven significant investments in training Deep Neural Networks (DNNs). However, these models that require resource-intensive training are vulnerable to theft and unauthorized use. This paper addresses this challenge by introducing DNNShield, a novel approach for DNN protection that integrates seamlessly before training. DNNShield embeds unique identifiers within the model architecture using specialized protection layers. These layers enable secure training and deployment while offering high resilience against …

addresses arxiv challenge cs.cr investments machine machine learning network networks neural network neural networks novel ownership protection resource theft training unauthorized verification vulnerable