TS-Inverse: A Gradient Inversion Attack tailored for Federated Time Series Forecasting Models
conference paper
Federated learning (FL) for time series forecasting (TSF) enables clients with privacy-sensitive time series (TS) data to collaboratively learn accurate forecasting models, e.g., in energy load prediction. Unfortunately, privacy risks in FL persist, as servers can potentially reconstruct clients’ training data through gradient inversion attacks (GIA). While GIA is demonstrated for image classification tasks, little is known for time series regression tasks. In this paper, we first conduct an extensive empirical study on inverting TS data across 4 TSF models and 4 datasets, identifying the unique challenges of reconstructing both observations and targets of TS data. We then propose TS-Inverse, a novel GIA that improves the inversion of TS data through (i) learning a gradient inversion model that outputs quantile predictions, (ii) a unique loss function incorporating periodicity and trend regularization, and (iii) regularization according to the quantile predictions. Our evaluations demonstrate a remarkable performance of TS-Inverse, achieving at least 2x-10x improvement in terms of sMAPE metric over existing GIA methods on TS data.
TNO Identifier
1003556
Source title
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Copenhagen, Denmark, 2025
Files
To receive the publication files, please send an e-mail request to TNO Repository.