Towards Zero Rotation and Beyond: Architecting Neural Networks for Fast Secure Inference with Homomorphic Encryption

Authors: Yifei Cai, Yizhou Feng, Qiao Zhang, Chunsheng Xin, Hongyi Wu
Published: 2026-01-29

Source: https://arxiv.org/abs/2601.21287

PDF: https://arxiv.org/pdf/2601.21287

AIにより推定されたラベル

アルゴリズム設計 暗号化技術 トリガーの検知

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Privacy-preserving deep learning addresses privacy concerns in Machine Learning as a Service (MLaaS) by using Homomorphic Encryption (HE) for linear computations. However, the computational overhead remains a major challenge. While prior work has improved efficiency, most approaches build on models originally designed for plaintext inference. Such models incur architectural inefficiencies when adapted to HE. We argue that substantial gains require networks tailored to HE rather than retrofitting plaintext architectures. Our design has two components: the building block and the overall architecture. First, StriaBlock targets the most expensive HE operation, rotation. It integrates ExRot-Free Convolution and a novel Cross Kernel, eliminating external rotations and requiring only 19