HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data

arxiv(2023)

引用 2|浏览11
暂无评分
摘要
Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic Encryption (HE), which allows performing computation on encrypted data. Most HE schemes work in a SIMD fashion, and the data packing method can dramatically affect the running time and memory costs. Finding a packing method that leads to an optimal performant implementation is a hard task. We present a simple and intuitive framework that abstracts the packing decision for the user. We explain its underlying data structures and optimizer, and propose a novel algorithm for performing 2D convolution operations. We used this framework to implement an HE-friendly version of AlexNet, which runs in three minutes, several orders of magnitude faster than other state-of-the-art solutions that only use HE.
更多
查看译文
关键词
tile tensors framework,large neural networks,neural networks,helayers
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要