Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection

by   Ruixiang Tang, et al.

In this paper, we introduce DSN (Deep Serial Number), a new watermarking approach that can prevent the stolen model from being deployed by unauthorized parties. Recently, watermarking in DNNs has emerged as a new research direction for owners to claim ownership of DNN models. However, the verification schemes of existing watermarking approaches are vulnerable to various watermark attacks. Different from existing work that embeds identification information into DNNs, we explore a new DNN Intellectual Property Protection mechanism that can prevent adversaries from deploying the stolen deep neural networks. Motivated by the success of serial number in protecting conventional software IP, we introduce the first attempt to embed a serial number into DNNs. Specifically, the proposed DSN is implemented in the knowledge distillation framework, where a private teacher DNN is first trained, then its knowledge is distilled and transferred to a series of customized student DNNs. During the distillation process, each customer DNN is augmented with a unique serial number, i.e., an encrypted 0/1 bit trigger pattern. Customer DNN works properly only when a potential customer enters the valid serial number. The embedded serial number could be used as a strong watermark for ownership verification. Experiments on various applications indicate that DSN is effective in terms of preventing unauthorized application while not sacrificing the original DNN performance. The experimental analysis further shows that DSN is resistant to different categories of attacks.


page 1

page 2

page 3

page 4


DNN Intellectual Property Protection: Taxonomy, Methods, Attack Resistance, and Evaluations

The training and creation of deep learning model is usually costly, thus...

Robust and Lossless Fingerprinting of Deep Neural Networks via Pooled Membership Inference

Deep neural networks (DNNs) have already achieved great success in a lot...

PCPT and ACPT: Copyright Protection and Traceability Scheme for DNN Model

Deep neural networks (DNNs) have achieved tremendous success in artifici...

Self-supervised Knowledge Distillation Using Singular Value Decomposition

To solve deep neural network (DNN)'s huge training dataset and its high ...

Performance Comparison of Contemporary DNN Watermarking Techniques

DNNs shall be considered as the intellectual property (IP) of the model ...

Customized Watermarking for Deep Neural Networks via Label Distribution Perturbation

With the increasing application value of machine learning, the intellect...

A survey of deep neural network watermarking techniques

Protecting the Intellectual Property Rights (IPR) associated to Deep Neu...