Low Latency Privacy Preserving Inference

By Alon Brutzkus, Oren Elisha, Ran Gilad-Bachrach. International Conference on Machine Learning, 2018

296 citations recorded by the source corpus.

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while protecting against information leakage. However, these methods are limited by the width and depth of neural networks that can be used (and hence the accuracy) and exhibit high latency even for relatively simple networks. In this study we provide two solutions that address these limitations. In the first solution, we present more than 10× improvement in latency and enable inference on wider networks compared to prior attempts with the same level of security. The improved performance is achieved by novel methods to represent the data during the computation. In the second solution, we apply the method of transfer learning to provide private inference services using deep networks with latency of ∼0.16 seconds. We demonstrate the efficacy of our methods on several computer vision tasks.

View Paper: https://www.semanticscholar.org/paper/610c67ffebfcd256b876f0dc6fa4cb75fbf9140d

How researchers see this paper

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

Citations in the corpus

Cheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference (2020, methodology): “Techniques can be categorized into two groups: HE only [11], [29], [32], [55], or multiparty computation (MPC)- based [33], [37], [50], [51].”
F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (2021, methodology): “Neural network benchmarks come from Low Latency CryptoNets (LoLa) [15].”
A Study of Face Obfuscation in ImageNet (2021, background): “Machine learning service providers can run their models on users’ private data encrypted using homomorphic encryption (Gilad-Bachrach et al., 2016; Brutzkus et al., 2019; Juvekar et al., 2018; Bian et al., 2020; Yonetani et al., 2017).”
A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “HE-based PPML uses encrypted datasets for model training or querying [15].”
Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (2022, methodology): “However state-of-the-art HE-based protocols [7, 8, 11, 23, 36] in the existing 2PC-NN systems force them to export the additive secret to the prime field Zp but not to the more efficient choice Z2` .”