Hercules: Boosting the performance of privacy-preserving federated learning

• Main Authors: XU, Guowen, HAN, Xingshuo, XU, Shengmin, ZHANG, Tianwei, LI, Hongwei, HUANG, Xinyi, DENG, Robert H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: federated learning; polynomial approximation; Privacy protection; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/8397; https://ink.library.smu.edu.sg/context/sis_research/article/9400/viewcontent/2207.04620__1_.pdf
• Institution: Singapore Management University

In this paper, we address the problem of privacy-preserving federated neural network training with N users. We present Hercules, an efficient and high-precision training framework that can tolerate collusion of up to N−1 users. Hercules follows the POSEIDON framework proposed by Sav et al. (NDSS’21), but makes a qualitative leap in performance with the following contributions: (i) we design a novel parallel homomorphic computation method for matrix operations, which enables fast Single Instruction and Multiple Data (SIMD) operations over ciphertexts. For the multiplication of two h×h dimensional matrices, our method reduces the computation complexity from O(h3) to O(h) . This greatly improves the training efficiency of the neural network since the ciphertext computation is dominated by the convolution operations; (ii) we present an efficient approximation on the sign function based on the composite polynomial approximation. It is used to approximate non-polynomial functions (i.e., ReLU and max ), with the optimal asymptotic complexity. Extensive experiments on various benchmark datasets (BCW, ESR, CREDIT, MNIST, SVHN, CIFAR-10 and CIFAR-100) show that compared with POSEIDON, Hercules obtains up to 4% increase in model accuracy, and up to 60× reduction in the computation and communication cost.