Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryption

Takumi Ishiyama, Takuya Suzuki, Hayato Yamana

研究成果: Conference contribution

抄録

In the big data era, cloud-based machine learning as a service (MLaaS) has attracted considerable attention. However, when handling sensitive data, such as financial and medical data, a privacy issue emerges, because the cloud server can access clients' raw data. A common method of handling sensitive data in the cloud uses homomorphic encryption, which allows computation over encrypted data without decryption. Previous research adopted a low-degree polynomial mapping function, such as the square function, for data classification. However, this technique results in low classification accuracy. This study seeks to improve the classification accuracy for inference processing in a convolutional neural network (CNN) while using homomorphic encryption. We apply various orders of the polynomial approximations of Google's Swish and ReLU activation functions. We also adopt batch normalization to normalize the inputs for the approximated activation functions to fit the input range to minimize the error. We implemented CNN inference labeling over homomorphic encryption using the Microsoft's Simple Encrypted Arithmetic Library (SEAL) for the Cheon-Kim-Kim-Song (CKKS) scheme. The experimental evaluations confirmed classification accuracies of 99.29% and 81.06% for MNIST and CIFAR-10, respectively, which entails 0.11% and 4.69% improvements, respectively, over previous methods.

本文言語English
ホスト出版物のタイトルProceedings - 2020 IEEE International Conference on Big Data, Big Data 2020
編集者Xintao Wu, Chris Jermaine, Li Xiong, Xiaohua Tony Hu, Olivera Kotevska, Siyuan Lu, Weijia Xu, Srinivas Aluru, Chengxiang Zhai, Eyhab Al-Masri, Zhiyuan Chen, Jeff Saltz
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3989-3995
ページ数7
ISBN(電子版)9781728162515
DOI
出版ステータスPublished - 2020 12 10
イベント8th IEEE International Conference on Big Data, Big Data 2020 - Virtual, Atlanta, United States
継続期間: 2020 12 102020 12 13

出版物シリーズ

名前Proceedings - 2020 IEEE International Conference on Big Data, Big Data 2020

Conference

Conference8th IEEE International Conference on Big Data, Big Data 2020
国/地域United States
CityVirtual, Atlanta
Period20/12/1020/12/13

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 情報システム
  • 情報システムおよび情報管理
  • 安全性、リスク、信頼性、品質管理

フィンガープリント

「Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryption」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル