Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?

by   Héber H. Arcolezi, et al.

This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy guarantee in two different and independent steps when training deep learning models. On one hand, we considered gradient perturbation, which uses the differentially private stochastic gradient descent algorithm to guarantee the privacy of each time series sample in the learning stage. On the other hand, we considered input perturbation, which adds differential privacy guarantees in each sample of the series before applying any learning. We compared four state-of-the-art recurrent neural networks: Long Short-Term Memory, Gated Recurrent Unit, and their Bidirectional architectures, i.e., Bidirectional-LSTM and Bidirectional-GRU. Extensive experiments were conducted with a real-world multivariate mobility dataset, which we published openly along with this paper. As shown in the results, differentially private deep learning models trained under gradient or input perturbation achieve nearly the same performance as non-private deep learning models, with loss in performance varying between 0.57% to 2.8%. The contribution of this paper is significant for those involved in urban planning and decision-making, providing a solution to the human mobility multivariate forecast problem through differentially private deep learning models.


page 1

page 2

page 3

page 4


Differentially Private Empirical Risk Minimization with Input Perturbation

We propose a novel framework for the differentially private ERM, input p...

Differentially Private Aggregated Mobility Data Publication Using Moving Characteristics

With the rapid development of GPS enabled devices (smartphones) and loca...

Improving the Algorithm of Deep Learning with Differential Privacy

In this paper, an adjustment to the original differentially private stoc...

Privacy Guarantees for Personal Mobility Data in Humanitarian Response

Personal mobility data from mobile phones and other sensors are increasi...

OptStream: Releasing Time Series Privately

Many applications of machine learning and optimization operate on data s...

The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets

Machine learning models based on neural networks and deep learning are b...

Efficient Per-Example Gradient Computations in Convolutional Neural Networks

Deep learning frameworks leverage GPUs to perform massively-parallel com...

Please sign up or login with your details

Forgot password? Click here to reset