SSAT: Active Authorization Control and User’s Fingerprint Tracking Framework for DNN IP Protection
Open Access
- 29 October 2024
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (10) , 1-24
Abstract
As training a high-performance deep neural network (DNN) model requires a large amount of data, powerful computing resources and expert knowledge, protecting well-trained DNN models from intellectual property (IP) infringement has raised serious concerns in recent years. Most existing methods using DNN watermarks to verify the ownership of the models after IP infringement occurs, which is reactive in the sense that they cannot prevent unauthorized users from using the model in the first place. Different from these methods, in this article, we propose an active authorization control and user’s fingerprint tracking method for the IP protection of DNN models by utilizing sample-specific backdoor attack. The proposed method inversely and multiplely exploits sample-specific trigger as the key to implement authorization control for DNN model, in which the generated triggers are imperceptible and sample-specific for clean images. Specifically, a U-Net model is used to generate backdoor instances. Then, the target model is trained on the clean images and backdoor instances, which are inversely labeled as wrong classes and correct classes, respectively. Only authorized users can use the target model normally by pre-processing the clean images through the U-Net model. Moreover, the images processed by the U-Net model will contain unique fingerprint that can be extracted to verify and track the corresponding user’s identity. This article is the first work that utilizes the sample-specific backdoor attack to implement active authorization control and user’s fingerprint management for DNN model under black-box scenarios. Extensive experimental results on ImageNet dataset and YouTube Aligned Face dataset demonstrate that the proposed method is effective in protecting the DNN model from unauthorized usage. Specifically, the protected model has a low inference accuracy (1.00%) for unauthorized users, while maintaining a normal inference accuracy (97.67%) for authorized users. Besides, the proposed method can achieve 100% fingerprint tracking success rates on both the ImageNet and YouTube Aligned Face datasets. Moreover, it is demonstrated that the proposed method is robust against fine-tuning attack, pruning attack, pruning attack with retraining, reverse-engineering attack, adaptive attack, and JPEG compression attack. The code is available at https://github.com/nuaaaisec/SSAT .Keywords
Funding Information
- National Natural Science Foundation of China (62372231)
- Aeronautical Science Foundation (2022Z071052008)
- CCF-NSFOCUS Kun-Peng Scientific Research Fund (CCF-NSFOCUS 2021012)
This publication has 42 references indexed in Scilit:
- Sample-Specific Backdoor based Active Intellectual Property Protection for Deep Neural Networks2022
- A Buyer-traceable DNN Model IP Protection Method Against Piracy and Misappropriation2022
- Active intellectual property protection for deep neural networks through stealthy backdoor and users’ identities authenticationApplied Intelligence, 2022
- AFA: Adversarial fingerprinting authentication for deep neural networksComputer Communications, 2020
- Adversarial frontier stitching for remote neural network watermarkingNeural Computing and Applications, 2019
- Deep Residual Learning for Image Recognition2016
- Face recognition in unconstrained videos with matched background similarity2011
- ImageNet: A large-scale hierarchical image database2009
- Quantization index modulation: a class of provably good methods for digital watermarking and information embeddingIEEE Transactions on Information Theory, 2001
- The JPEG still picture compression standardIEEE Transactions on Consumer Electronics, 1992