Differentially private multivariate time series forecasting of aggregated human mobility with deep learning: Input or gradient perturbation?

Abstract

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 Héber H.

Special issue on deep learning for time series data

“…The authors generated synthetic multivariate time series data that are statistically similar to the real data and improved the flare prediction performance. Arcolezi et al [14] investigate the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the concerned individuals. The authors provided a comparative evaluation of differentially private deep learning models in both input and gradient perturbation settings to forecast multivariate aggregated mobility time series data.…”