Please use this identifier to cite or link to this item:
|Title:||A DNN fingerprint for non-repudiable model ownership identification and piracy detection||Authors:||Zheng, Yue
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|
Updated on Nov 25, 2022
Updated on Nov 25, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.