Extending Null Embedding for Deep Neural Network (DNN) Watermarking
Kaan Altınay (Student TU Delft)
Devri İş Ler (IMDEA Networks Institute, Carlos III University of Madrid)
Zekeriya Erkin (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
The rise of Machine Learning (ML) has opened new business opportunities, particularly through Machine Learning as a Service (MLaaS), where costly models like Deep Neural Networks (DNNs) can be outsourced. However, this also raises concerns about model piracy. To protect against unauthorized use, watermarking techniques have been developed. One such method, null embedding by Li et al., disables the model if pirated but reduces classification accuracy. This paper proposes modifications to the null-embedding technique that reduce this impact and keep the classification accuracy close to that of a non-watermarked model.
help_outline