A DNN Fingerprint for Non-Repudiable Model Ownership Identification and Piracy Detection
Open Access
- 11 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 2977-2989
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 non-repudiable 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.Keywords
Funding Information
- National Research Foundation, Singapore, under its National Cybersecurity Research and Development Programme/Cyber-Hardware Forensic & Assurance Evaluation Research and Development Programme (CHFAGC1-AW01)
This publication has 15 references indexed in Scilit:
- AFA: Adversarial fingerprinting authentication for deep neural networksComputer Communications, 2020
- Bit-Flip Attack: Crushing Neural Network With Progressive Bit Search2019
- Adversarial frontier stitching for remote neural network watermarkingNeural Computing and Applications, 2019
- A PUF-Based Data-Device Hash for Tampered Image Detection and Source Camera IdentificationIEEE Transactions on Information Forensics and Security, 2019
- DeepAttest2019
- UDhashing: Physical Unclonable Function-Based User-Device Hash for Endpoint AuthenticationIEEE Transactions on Industrial Electronics, 2019
- Densely Connected Convolutional Networks2017
- Embedding Watermarks into Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- An elementary proof of a theorem of Johnson and LindenstraussRandom Structures & Algorithms, 2002