Challenges of Privacy-Preserving Machine Learning in IoT

TL;DR

This paper reviews privacy-preserving machine learning methods for IoT, discusses challenges in deploying them, and proposes a lightweight inference approach that balances privacy and classification accuracy.

Contribution

It provides a taxonomy of existing approaches, discusses IoT-specific challenges, and introduces a new lightweight inference method for privacy preservation.

Findings

Satisfactory performance on MNIST dataset

Effective obfuscation of data before transmission

Addresses IoT-specific privacy challenges

Abstract

The Internet of Things (IoT) will be a main data generation infrastructure for achieving better system intelligence. However, the extensive data collection and processing in IoT also engender various privacy concerns. This paper provides a taxonomy of the existing privacy-preserving machine learning approaches developed in the context of cloud computing and discusses the challenges of applying them in the context of IoT. Moreover, we present a privacy-preserving inference approach that runs a lightweight neural network at IoT objects to obfuscate the data before transmission and a deep neural network in the cloud to classify the obfuscated data. Evaluation based on the MNIST dataset shows satisfactory performance.