ArchNet: A data hiding design for distributed machine learning systems

Kaiyan Chang

doi:10.1016/j.sysarc.2020.101912

ArchNet: A data hiding design for distributed machine learning systems

2021-03-01

0

OA

AI

DOI：10.1016/j.sysarc.2020.101912

Original

Save

View PDF

Abstract

En 中文

Integrating idle embedded devices into cloud computing is a promising approach to support Distributed Machine Learning (DML). In this paper, we approach to address the data hiding problem in such DML systems. For the purpose of the data encryption in DML systems, we introduce the tripartite asymmetric encryption theorem to provide theoretical support. Based on the theorem, we design a general image encryption scheme (called ArchNet), which can encrypt original images via the encoder to resist against illegal users. ArchNet encrypts the dataset by a specific neural network, which is especially trained for encryption. The encrypted data can be easily recognized by deep learning model. However, the encrypted data cannot be recognized by human, which makes the illegal attacker difficult to steal the encrypted data. We use MNIST, Fashion-MNIST and Cifar-10 datasets to evaluate efficiency of our design. We deploy certain base models on the encrypted datasets and compare them with the RC4 algorithm and differential privacy policy. Our design can improve the accuracy on MNIST up to 97.26% compared with RC4. The accuracies on these three datasets encrypted by ArchNet are similar to the base model. ArchNet can be deployed on DML systems with embedded devices.

Keywords:

Distributed machine learning

Data hiding

Neural networks

Embedded systems

Encryption

ArchNet: A data hiding design for distributed machine learning systems

Abstract

AI Summary

Journal

Organization