Blind Faith: Privacy-Preserving Machine Learning using Function Approximation

2021/07/29 by Tanveer Ahmed Khan, Khan, Tanveer, Alexandros Bakas +3 · 2 citations
Computer Science · #Cryptography and Data Security #Privacy-Preserving Technologies in Data #Chaos-based Image/Signal Encryption

paper · pdf · doi:10.48550/arxiv.2107.14338

Abstract

Over the past few years, a tremendous growth of machine learning was brought about by a significant increase in adoption of cloud-based services. As a result, various solutions have been proposed in which the machine learning models run on a remote cloud provider. However, when such a model is deployed on an untrusted cloud, it is of vital importance that the users' privacy is preserved. To this end, we propose Blind Faith -- a machine learning model in which the training phase occurs in plaintext data, but the classification of the users' inputs is performed on homomorphically encrypted ciphertexts. To make our construction compatible with homomorphic encryption, we approximate the activation functions using Chebyshev polynomials. This allowed us to build a privacy-preserving machine learning model that can classify encrypted images. Blind Faith preserves users' privacy since it can perform high accuracy predictions by performing computations directly on encrypted data.

Cited by

• DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inference
• Oops!... They Stole it Again: Attacks on Split Learning

Related

• Learning in the Dark: Privacy-Preserving Machine Learning using Function Approximation
• Blind Evaluation Framework for Fully Homomorphic Encryption and Privacy-Preserving Machine Learning
• PINFER: Privacy-Preserving Inference for Machine Learning
• Partially Encrypted Machine Learning using Functional Encryption
• PRISM: Privacy-preserving Inference System with Homomorphic Encryption and Modular Activation