Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162779
Title: A DNN fingerprint for non-repudiable model ownership identification and piracy detection
Authors: Zheng, Yue
Wang, Si
Chang, Chip Hong
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Source: Zheng, Y., Wang, S. & Chang, C. H. (2022). A DNN fingerprint for non-repudiable model ownership identification and piracy detection. IEEE Transactions On Information Forensics and Security, 17, 2977-2989. https://dx.doi.org/10.1109/TIFS.2022.3198267
Project: CHFA-GC1-AW01
Journal: IEEE Transactions on Information Forensics and Security 
Abstract: A high-performance Deep Neural Network (DNN) model is a valuable intellectual property (IP) since designing and training such a model from scratch is very costly. Model transfer learning, compression and retraining are commonly used by pirates to evade detection or even redeploy the pirated models for new applications without compromising performance. This paper presents a novel non-intrusive DNN IP fingerprinting method that can detect pirated models and provide a nonrepudiable and irrevocable ownership proof simultaneously. The fingerprint is derived from projecting a subset of front-layer weights onto a model owner identity defined random space to enable a distinguisher to differentiate pirated models that are used in the same application or retrained for a different task from originally designed DNN models. The proposed method generates compact and irrevocable fingerprints against model IP misappropriation and ownership fraud. It requires no retraining and makes no modification to the original model. The proposed fingerprinting method is evaluated on nine original DNN models trained on CIFAR-10, CIFAR-100, and ImageNet-10. It is demonstrated to have the highest discriminative power among existing fingerprinting methods in detecting pirated models deployed for the same and different applications, and fraudulent model IP ownership claims.
URI: https://hdl.handle.net/10356/162779
ISSN: 1556-6013
DOI: 10.1109/TIFS.2022.3198267
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/TIFS.2022.3198267.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Files in This Item:
File Description SizeFormat 
dnn_ip.pdfA DNN Fingerprint for Non-repudiable Model Ownership Identification and Piracy Detection2.91 MBAdobe PDFView/Open

Page view(s)

10
Updated on Nov 25, 2022

Download(s)

1
Updated on Nov 25, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.