Private Dataset Generation Using Privacy Preserving Collaborative Learning

TL;DR

This paper introduces FedCollabNN, a privacy-preserving, computationally efficient framework for training machine learning models at the edge, robust against adversarial attacks, demonstrated on the MNIST dataset.

Contribution

The paper presents FedCollabNN, a novel framework combining privacy preservation and robustness for edge-based deep learning training, addressing computational and security challenges.

Findings

Effective privacy preservation demonstrated on MNIST

Framework is computationally efficient

Robust against adversarial attacks

Abstract

With increasing usage of deep learning algorithms in many application, new research questions related to privacy and adversarial attacks are emerging. However, the deep learning algorithm improvement needs more and more data to be shared within research community. Methodologies like federated learning, differential privacy, additive secret sharing provides a way to train machine learning models on edge without moving the data from the edge. However, it is very computationally intensive and prone to adversarial attacks. Therefore, this work introduces a privacy preserving FedCollabNN framework for training machine learning models at edge, which is computationally efficient and robust against adversarial attacks. The simulation results using MNIST dataset indicates the effectiveness of the framework.