Secure Outsourced Matrix Computation and Application to Neural Networks

By Xiaoqian Jiang, Miran Kim, Kristin E. Lauter, Yongsoo Song. 2018

362 citations recorded by the source corpus.

Homomorphic Encryption (HE) is a powerful cryptographic primitive to address privacy and security issues in outsourcing computation on sensitive data to an untrusted computation environment. Comparing to secure Multi-Party Computation (MPC), HE has advantages in supporting non-interactive operations and saving on communication costs. However, it has not come up with an optimal solution for modern learning frameworks, partially due to a lack of efficient matrix computation mechanisms. In this work, we present a practical solution to encrypt a matrix homomorphically and perform arithmetic operations on encrypted matrices. Our solution includes a novel matrix encoding method and an efficient evaluation strategy for basic matrix operations such as addition, multiplication, and transposition. We also explain how to encrypt more than one matrix in a single ciphertext, yielding better amortized performance. Our solution is generic in the sense that it can be applied to most of the existing HE schemes. It also achieves reasonable performance for practical use; for example, our implementation takes 9.21 seconds to multiply two encrypted square matrices of order 64 and 2.56 seconds to transpose a square matrix of order 64. Our secure matrix computation mechanism has a wide applicability to our new framework EDM, which stands for encrypted data and encrypted model. To the best of our knowledge, this is the first work that supports secure evaluation of the prediction phase based on both encrypted data and encrypted model, whereas previous work only supported applying a plain model to encrypted data. As a benchmark, we report an experimental result to classify handwritten images using convolutional neural networks (CNN). Our implementation on the MNIST dataset takes 28.59 seconds to compute ten likelihoods of 64 input images simultaneously, yielding an amortized rate of 0.45 seconds per image.

Subfields: Education

How researchers see this paper

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

1. M. Sadegh Riazi
2. Hao Chen
3. Kim Laine
4. Zhicong Huang
5. Miran Kim
6. Wei Dai
7. Blake Pelton
8. Yongsoo Song

Citations in the corpus

• HEAX: An Architecture for Computing on Encrypted Data (2019, background): “Several works [40, 43] have shown the benefits of choosing the CKKS scheme over other schemes when an approximate computation is required, e.g., in Machine Learning applications.”
• Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (2022, background): “1) Optimizations for the basic operations of NN such as convolutions [11, 36], matrix multiplications [35, 43] and non-linear activation functions [20].”
• XONN: XNOR-based Oblivious Deep Neural Network Inference (2019, methodology): “In E2DM framework [31], the model owner can encrypt and outsource the model to an untrusted server to perform oblivious inference.”
• Efficient Multi-Key Homomorphic Encryption with Packed Ciphertexts with Application to Oblivious Neural Network Inference (2019, background): “In Table 6, we compare our benchmark result with the state-of-the-art frameworks for oblivious neural network inference: CryptoNets [29], MiniONN [42], Gazelle [35], and E2DM [34].”
• HEAX: High-Performance Architecture for Computation on Homomorphically Encrypted Data in the Cloud (2019, background): “Privacy-preserving MLaaS has been studied rigorously in recent years and several protocol-level and algorithmic improvements have been proposed [36, 48, 63, 46, 19, 64, 62, 61, 42].”