ActiveGuard: An active intellectual property protection technique for deep neural networks by leveraging adversarial examples as users' fingerprints
Abstract The intellectual properties (IP) protection of deep neural networks (DNN) models has raised many concerns in recent years. To date, most of the existing works use DNN watermarking to protect the IP of DNN models. However, the DNN watermarking methods can only passively verify the copyright...
Main Authors: | Mingfu Xue, Shichang Sun, Can He, Dujuan Gu, Yushu Zhang, Jian Wang, Weiqiang Liu |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-IET
2023-07-01
|
Series: | IET Computers & Digital Techniques |
Subjects: | |
Online Access: | https://doi.org/10.1049/cdt2.12056 |
Similar Items
-
A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach
by: Mohammed Nasser Al-Andoli, et al.
Published: (2024-01-01) -
Random Untargeted Adversarial Example on Deep Neural Network
by: Hyun Kwon, et al.
Published: (2018-12-01) -
AdvGuard: Fortifying Deep Neural Networks Against Optimized Adversarial Example Attack
by: Hyun Kwon, et al.
Published: (2024-01-01) -
Adversarial Data Hiding in Digital Images
by: Dan Wang, et al.
Published: (2022-05-01) -
Maxwell’s Demon in MLP-Mixer: towards transferable adversarial attacks
by: Haoran Lyu, et al.
Published: (2024-03-01)