Amalgam: A Framework for Obfuscated Neural Network Training on the Cloud

TL;DR

Amalgam is a framework that enables privacy-preserving training of neural networks on the cloud by augmenting models and datasets with noise, effectively hiding proprietary information without compromising accuracy.

Contribution

This paper introduces Amalgam, a novel framework for obfuscating neural network models and datasets during cloud training, ensuring privacy without accuracy loss.

Findings

Modest training overheads introduced by Amalgam

No impact on model accuracy

Effective hiding of model architecture and data

Abstract

Training a proprietary Neural Network (NN) model with a proprietary dataset on the cloud comes at the risk of exposing the model architecture and the dataset to the cloud service provider. To tackle this problem, in this paper, we present an NN obfuscation framework, called Amalgam, to train NN models in a privacy-preserving manner in existing cloud-based environments. Amalgam achieves that by augmenting NN models and the datasets to be used for training with well-calibrated noise to "hide" both the original model architectures and training datasets from the cloud. After training, Amalgam extracts the original models from the augmented models and returns them to users. Our evaluation results with different computer vision and natural language processing models and datasets demonstrate that Amalgam: (i) introduces modest overheads into the training process without impacting its correctness, and (ii) does not affect the model's accuracy. The prototype implementation is available at: https://github.com/SifatTaj/amalgam