Multi-key privacy-preserving deep learning in cloud computing

By Ping Li, Jin Li, Zhengan Huang, Tong Li, Chong-zhi Gao, Siu Ming Yiu, Kai Chen. 2017

452 citations recorded by the source corpus.

Deep learning has attracted a lot of attention and has been applied successfully in many areas such as bioinformatics, imaging processing, game playing and computer security etc. On the other hand, deep learning usually requires a lot of training data which may not be provided by a sole owner. As the volume of data gets huge, it is common for users to store their data in a third-party cloud. Due to the confidentiality of the data, data are usually stored in encrypted form. To apply deep learning to these datasets owned by multiple data owners on cloud, we need to tackle two challenges: (i) the data are encrypted with different keys, all operations including intermediate results must be secure; and (ii) the computational cost and the communication cost of the data owner(s) should be kept minimal. In our work, we propose two schemes to solve the above problems. We first present a basic scheme based on multi-key fully homomorphic encryption (MK-FHE), then we propose an advanced scheme based on a hybrid structure by combining the double decryption mechanism and fully homomorphic encryption (FHE). We also prove that these two multi-key privacy-preserving deep learning schemes over encrypted data are secure. In the basic scheme, we use M-FHE as our privacy-preserving technique. Only the decrypt operation needs the interaction among data owners.In the advanced scheme, we propose a hybrid structure scheme by combining the double decryption mechanism and FHE.In the advanced scheme, only the encrypt and decrypt algorithms are performed by data providers.We prove that these two multi-key privacy-preserving deep learning schemes over encrypted data are secure.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bingsheng He
2. Qinbin Li
3. Zeyi Wen
4. Zhaomin Wu
5. Qiang Yang
6. Ming Ding
7. Chunyan Miao
8. Houbing Song

Citations in the corpus

• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, methodology): “protection: cryptographic methods and differential privacy. Cryptographic methods such as homomorphic encryption[15, 77, 27, 33, 74, 145, 146, 204, 206, 112], and secure multi-party computation (SMC) [157, 36, 23, 51, 24, 101, 17, 62, 91, 181, 39, 65] are widely used in privacy-preserving machine le”
• When Machine Learning Meets Privacy (2020, methodology): “…support vector machine (SVM) learning mechanisms by adding noise to the output classifier and they yield close approximations to the non-private SVM. Chaudhuri et al. [18] provided the model objective perturbation to produce deferentially private empirical risk minimization (ERM) classifier.”
• Differential Privacy for Deep and Federated Learning: A Survey (2022, background): “, original dataset) of the dataset [25], [26].”
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “devices and smartphones such as measurements [5], photos [6], videos [7], and location information [8] are aggregated at the data center [9].”
• Privacy‐preserving federated learning based on multi‐key homomorphic encryption (2021, methodology): “Improved schemes have been proposed in [38], [7] using addictive homomorphic encryption to protect model updates, by Zhang et al.”
• A Decade Survey of Transfer Learning (2010–2020) (2020, methodology): “What is more, many privacy-preserving methods have been adopted to supervised learning algorithms [116].”
• A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends (2018, background): “[77] proposed multiple schemes for machine learning on multi-key homomorphic encrypted data in the cloud.”
• Data Security and Privacy Protection for Cloud Storage: A Survey (2020, background): “for example, machine learning with public auditing [41], machine learning training and classification scheme based on homomorphic encryption [54], and homomorphic deep learning [57].”