Please use this identifier to cite or link to this item:
|Title:||A buyer-traceable DNN model IP protection method against piracy and misappropriation||Authors:||Wang, Si
Chang, Chip Hong
|Keywords:||Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision||Issue Date:||2022||Source:||Wang, S., Xu, C., Zheng, Y. & Chang, C. H. (2022). A buyer-traceable DNN model IP protection method against piracy and misappropriation. 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS). https://dx.doi.org/10.1109/AICAS54282.2022.9869923||Project:||CHFA-GC1-AW01||metadata.dc.contributor.conference:||2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)||Abstract:||Recently proposed model functionality and attribute extraction techniques have exacerbated unauthorized low-cost reproduction of deep neural network (DNN) models for similar applications. In particular, intellectual property (IP) theft and unauthorized distribution of DNN models by dishonest buyers are very difficult to trace by existing framework of digital rights management (DRM). This paper presents a new buyer-traceable DRM scheme against model piracy and misappropriation. Unlike existing methods that require white-box access to extract the latent information for verification, the proposed method utilizes data poisoning for distributorship embedding and black-box verification. Composite backdoors are installed into the target model during the training process. Each backdoor is created by applying a data augmentation method to some clean images of a selected class. The data-augmented images with a wrong label associated with a buyer are injected into the training dataset. The ownership and distributorship of a backdoor-trained user model can be validated by querying the suspect model with a set of composite triggers. A positive suspect will output the dirty labels that pinpoint the dishonest buyer while an innocent model will output the correct labels with high confidence. The tracking accuracy and robustness of the proposed IP protection method are evaluated on CIFAR-10, CIFAR-100 and GTSRB datasets for different applications. The results show an average of 100% piracy detection rate, 0% false positive rate and 96.81% traitor tracking success rate with negligible model accuracy degradation.||URI:||https://hdl.handle.net/10356/159395||ISBN:||978-1-6654-0996-4||DOI:||10.1109/AICAS54282.2022.9869923||Schools:||School of Electrical and Electronic Engineering||Research Centres:||VIRTUS, IC Design Centre of Excellence||Rights:||© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/AICAS54282.2022.9869923.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Conference Papers|
Updated on Sep 21, 2023
Updated on Sep 21, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.