DeepContract: Controllable Authorization of Deep Learning Models
Open Access
- 4 December 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 609-620
Abstract
Well-trained deep learning (DL) models are widely used in various fields and recognized as valuable intellectual property. However, most existing efforts to fully exploit their value either require users to upload input data to provide machine learning services, which raises serious privacy concerns, or deploy DL models on the user side, resulting in a loss of control over the models. While a few active model authorization methods protect the model from unauthorized users, they cannot prevent the model from being redistributed or abused by authorized users. To address the urgent need to efficiently protect both model confidentiality and input data privacy, and achieve uninterrupted model controllability, we propose a contract-based model authorization framework called DeepContract. This framework enables model owners to deploy their models on the user side for local inference without revealing original model weights. Moreover, it allows them to grant and revoke the right to use their models at any time. Specifically, we propose a generic model encryption method that significantly outperforms the state-of-the-art method in both efficiency and security. Leveraging the integrity verification in the Trusted Execution Environment, contract-based and verifiable enclave codes generated by DeepContract can perform controlled inference using the encrypted model distributed on the user side. Our extensive evaluations show that DeepContract can achieve efficient and secure controllable model authorization for the pre-signed contract.Keywords
Funding Information
- The National Key R&D Program of China (2021YFB2900103)
- The University Synergy Innovation Program of Anhui Province (GXXT-2022-049)
- the Fundamental Research Funds for the Central Universities (WK2150110024)
- China National Natural Science Foundation (61932016)
This publication has 22 references indexed in Scilit:
- Chameleon2018
- P esos2018
- Oblivious Neural Network Predictions via MiniONN Transformations2017
- Embedding Watermarks into Deep Neural Networks2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- SecureML: A System for Scalable Privacy-Preserving Machine Learning2017
- Deep Residual Learning for Image Recognition2016
- MLaaS: Machine Learning as a Service2015
- Going deeper with convolutions2015
- Symmetric Ciphers Based on Two-Dimensional Chaotic MapsInternational Journal of Bifurcation and Chaos, 1998