mlsanityData to 14 Oct 2026

TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Models

arXiv 2503.20952 ↗First posted 26 Mar 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) for time series forecasting (TSF) enables clients with privacy-sensitive time series (TS) data to collaboratively learn accurate forecasting models, for example, in energy load prediction. Unfortunately, privacy risks in FL persist, as servers can potentially reconstruct clients' training data through gradient inversion attacks (GIA). Although GIA is demonstrated for image classification tasks, little is known about 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 by (i) learning a gradient inversion model that outputs quantile predictions, (ii) a unique loss function that incorporates periodicity and trend regularization, and (iii) regularization according to the quantile predictions. Our evaluations demonstrate a remarkable performance of TS-Inverse, achieving at least a 2x-10x improvement in terms of the sMAPE metric over existing GIA methods on TS data. Code repository: https://github.com/Capsar/ts-inverse

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

30 of 45 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  5. 2019Deep Leakage from Gradientscited by 1,021
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  7. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 571
  8. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  10. 2017Sparse Communication for Distributed Gradient Descentcited by 249
  11. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  12. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
18 more
  1. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  2. 2021Gradient Inversion with Generative Image Priorcited by 101
  3. 2020R-GAP: Recursive Gradient Attack on Privacycited by 97
  4. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  5. 2021TAG: Gradient Attack on Transformer-based Language Modelscited by 63
  6. 2021Towards General Deep Leakage in Federated Learningcited by 40
  7. 2022Delving into Effective Gradient Matching for Dataset Condensationcited by 40
  8. 2022Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learningcited by 30
  9. 2020SAPAG: A Self-Adaptive Privacy Attack From Gradientscited by 27
  10. 2020Layer-wise Characterization of Latent Information Leakage in Federated Learningcited by 19
  11. 2022AGIC: Approximate Gradient Inversion Attack on Federated Learningcited by 15
  12. 2022TabLeak: Tabular Data Leakage in Federated Learningcited by 13
  13. 2022Dropout is NOT All You Need to Prevent Gradient Leakagecited by 11
  14. 2024Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matchingcited by 8
  15. 2023Crossing Roads of Federated Learning and Smart Grids: Overview, Challenges, and Perspectivescited by 6
  16. 2021Dropout against Deep Leakage from Gradientscited by 4
  17. 2021Privacy-preserving Federated Learning for Residential Short Term Load Forecastingcited by 4
  18. 2024Exploring Lightweight Federated Learning for Distributed Load Forecastingcited by 2

Built on by

Not cited yet.