EQO: Exploring Ultra-Efficient Private Inference with Winograd-Based Protocol and Quantization Co-Optimization

arXiv:2404.09404v1 Announce Type: new
Abstract: Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose EQO, a quantized 2PC inference framework that jointly optimizes the CNNs and 2PC protocols. EQO features a novel 2PC protocol that combines Winograd transformation with quantization for efficient convolution computation. However, we observe naively combining quantization and Winograd convolution is sub-optimal: Winograd transformations introduce extensive local additions …

arxiv cnn cnns communication computation cs.cr features framework high latency network neural network optimization party private protocol protocols ultra