Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning

2019/04/12 by Chun-Hsien Yu, Yu, Chun-Hsien, Chun-Nan Chou +3 · 1 citation
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1904.06049

accepted by IEEE MIPR'19 - short paper

arxiv created 2019/04/12 · arxiv updated 2019/04/15

Abstract

Deep Learning techniques have achieved remarkable results in many domains. Often, training deep learning models requires large datasets, which may require sensitive information to be uploaded to the cloud to accelerate training. To adequately protect sensitive information, we propose distributed layer-partitioned training with step-wise activation functions for privacy-preserving deep learning. Experimental results attest our method to be simple and effective.

Cited by

• Oops!... They Stole it Again: Attacks on Split Learning

Related

• Multiple Classification with Split Learning
• No Peek: A Survey of private distributed deep learning
• PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks
• A Quantization-based Technique for Privacy Preserving Distributed Learning
• CURE: Privacy-Preserving Split Learning Done Right