ArchNet: Data Hiding Model in Distributed Machine Learning System
arXiv:2004.10968 · doi:10.1016/j.sysarc.2020.101912
Abstract
Integrating idle embedded devices into cloud computing is a promising approach to support distributed machine learning. In this paper, we approach to address the data hiding problem in such distributed machine learning systems. For the purpose of the data encryption in the distributed machine learning systems, we propose the Tripartite Asymmetric Encryption theorem and give mathematical proof. Based on the theorem, we design a general image encryption scheme ArchNet.The scheme has been implemented on MNIST, Fashion-MNIST and Cifar-10 datasets to simulate real situation. We use different base models on the encrypted datasets and compare the results with the RC4 algorithm and differential privacy policy. Experiment results evaluated the efficiency of the proposed design. Specifically, our design can improve the accuracy on MNIST up to 97.26% compared with RC4.The accuracies on the datasets encrypted by ArchNet are 97.26%, 84.15% and 79.80%, and they are 97.31%, 82.31% and 80.22% on the original datasets, which shows that the encrypted accuracy of ArchNet has the same performance as the base model. It also shows that ArchNet can be deployed on the distributed system with embedded devices.
References in corpus (15)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Deep Residual Learning for Image Recognition
- Scalable Private Learning with PATE
- Gazelle: A Low Latency Framework for Secure Neural Network Inference
- Crypto-Nets: Neural Networks over Encrypted Data
- Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
- PRADA: Protecting against DNN Model Stealing Attacks
- nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
- Defending Against Machine Learning Model Stealing Attacks Using Deceptive Perturbations
- Deep Leakage from Gradients
- LEP-CNN: A Lightweight Edge Device Assisted Privacy-preserving CNN Inference Solution for IoT
- High-resolution imaging on TPUs
- Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls
- Representation of Federated Learning via Worst-Case Robust Optimization Theory
- Hardware Implementation of four byte per clock RC4 algorithm