DeepDIST: A Black-Box Anti-Collusion Framework for Secure Distribution of Deep Models
- 9 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (1) , 97-109
Abstract
Due to enormous computing and storage overhead for well-trained Deep Neural Network (DNN) models, protecting the intellectual property of model owners is a pressing need. As the commercialization of deep models is becoming increasingly popular, the pre-trained models delivered to users may suffer from being illegally copied, redistributed, or abused. In this paper, we propose DeepDIST, the first end-to-end secure DNNs distribution framework in a black-box scenario. Specifically, our framework adopts a dual-level fingerprint (FP) mechanism to provide reliable ownership verification, and proposes two equivalent transformations that can resist collusion attacks, plus a newly designed similarity loss term to improve the security of the transformations. Unlike the existing passive defense schemes that detect colluding participants, we introduce an active defense strategy, namely damaging the performance of the model after the malicious collusion. The extensive experimental results show that DeepDIST can maintain the accuracy of the host DNN after embedding fingerprint conducted for true traitor tracing, and is robust against several popular model modifications. Furthermore, the anti-collusion effect is evaluated on two typical classification tasks (10-class and 100-class), and the proposed DeepDIST can drop the prediction accuracy of the collusion model to 10% and 1% (random guess), respectively.Keywords
Funding Information
- National Natural Science Foundation of China (61702105, 62072109, 62172098)
- Natural Science Foundation of Fujian Province (2020J01497)
- Education Research Project for Young and Middle-Aged Teachers of the Education Department of Fujian Province (JAT200064)
This publication has 32 references indexed in Scilit:
- Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss2020
- DeepMarks2019
- DeepSigns2019
- Protecting Intellectual Property of Deep Neural Networks with Watermarking2018
- Trojaning Attack on Neural Networks2018
- Embedding Watermarks into Deep Neural Networks2017
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Group-Oriented Anti-Collusion Fingerprint Based on BIBD Code2010