Privacy-preserving Machine Learning as a Service

By Ehsan Hesamifard, Hassan Takabi, Mehdi Ghasemi, Rebecca N. Wright. 2018

275 citations recorded by the source corpus.

Abstract Machine learning algorithms based on deep Neural Networks (NN) have achieved remarkable results and are being extensively used in different domains. On the other hand, with increasing growth of cloud services, several Machine Learning as a Service (MLaaS) are offered where training and deploying machine learning models are performed on cloud providers’ infrastructure. However, machine learning algorithms require access to the raw data which is often privacy sensitive and can create potential security and privacy risks. To address this issue, we present CryptoDL, a framework that develops new techniques to provide solutions for applying deep neural network algorithms to encrypted data. In this paper, we provide the theoretical foundation for implementing deep neural network algorithms in encrypted domain and develop techniques to adopt neural networks within practical limitations of current homomorphic encryption schemes. We show that it is feasible and practical to train neural networks using encrypted data and to make encrypted predictions, and also return the predictions in an encrypted form. We demonstrate applicability of the proposed CryptoDL using a large number of datasets and evaluate its performance. The empirical results show that it provides accurate privacy-preserving training and classification.

Subfields: Artificial Intelligence, Privacy & Security

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

In Privacy & Security

Citations in the corpus

QUOTIENT: Two-Party Secure Neural Network Training and Prediction (2019, methodology): “While there have been massive practical developments in both cryptography and ML (including the works above), most recent works for model training [22, 40, 41, 54] and prediction [7, 15, 50] on encrypted data are largely based on optimizations for either the ML model or the employed cryptographic te”
Contamination Attacks and Mitigation in Multi-Party Machine Learning (2018, neutral): “Secure MPC can be enabled with cryptographic techniques [6, 11, 18, 29, 32], and systems based on trusted processors such as Intel SGX [3, 5, 33].”
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020, background): “67 Demonstrations to date have been carried out on commodity hardware (CPUs [113] [114] and GPUs [115]) or have secure and verifiable outsourcing of parts of the computation to less secure hardware [116] [117], rather than on hardware directly optimized for machine learning (such as TPUs).”
XONN: XNOR-based Oblivious Deep Neural Network Inference (2019, methodology): “CryptoDL [27] improves upon CryptoNets [19] and proposes more efﬁcient approximation of the non-linear functions using low-degree polynomials.”
When Machine Learning Meets Privacy (2020, methodology): “deepneuralnetworks(DNN).Dowlinetal.[29]proposed CryptoNets which demonstrates how to efficiently convert learned neural networks to make it applicable to encrypted input data. While Hesamifard et al. [54] proposed a framework to train the neural network over encrypted data. Li et al. [77] investigat”