XNET: A Real-Time Unified Secure Inference Framework Using Homomorphic Encryption

ePrint Report: XNET: A Real-Time Unified Secure Inference Framework Using Homomorphic Encryption

Hao Yang, Shiyu Shen, Siyang Jiang, Lu Zhou, Wangchen Dai, Yunlei Zhao

Homomorphic Encryption (HE) presents a promising solution to securing neural networks for Machine Learning as a Service (MLaaS). Despite its potential, the real-time applicability of current HE-based solutions remains a challenge, and the diversity in network structures often results in inefficient implementations and maintenance. To address these issues, we introduce a unified and compact network structure …

current dai encryption eprint report framework homomorphic encryption machine machine learning networks neural networks report service solution