Improving the Algorithm of Deep Learning with Differential Privacy
arXiv:2107.05457
Abstract
In this paper, an adjustment to the original differentially private stochastic gradient descent (DPSGD) algorithm for deep learning models is proposed. As a matter of motivation, to date, almost no state-of-the-art machine learning algorithm hires the existing privacy protecting components due to otherwise serious compromise in their utility despite the vital necessity. The idea in this study is natural and interpretable, contributing to improve the utility with respect to the state-of-the-art. Another property of the proposed technique is its simplicity which makes it again more natural and also more appropriate for real world and specially commercial applications. The intuition is to trim and balance out wild individual discrepancies for privacy reasons, and at the same time, to preserve relative individual differences for seeking performance. The idea proposed here can also be applied to the recurrent neural networks (RNN) to solve the gradient exploding problem. The algorithm is applied to benchmark datasets MNIST and CIFAR-10 for a classification task and the utility measure is calculated. The results outperformed the original work.
References in corpus (6)
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
- Renyi Differential Privacy
- Federated Learning for Mobile Keyboard Prediction
- Can You Really Backdoor Federated Learning?
- Differentially Private Learning with Adaptive Clipping
- Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising