Benchmarking Time Series Generation Methods for Privacy-Preserving Forecasting

• URL: http://arxiv.org/abs/2608.10891v1
• Date: Tue, 11 Aug 2026 13:09:01 GMT
• Title: Benchmarking Time Series Generation Methods for Privacy-Preserving Forecasting
• Abstract summary: Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations.<n>How well synthetic generation methods perform when fully replacing the original data remains underexplored.<n>This benchmark establishes a reference point for evaluating and developing new privacy-aware synthetic time series generation methods.
• Score: 2.7120006458149764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time series generation has been developed primarily for data augmentation, where generated series supplement the original training set. How well these methods perform when fully replacing the original data - and how much privacy risk the released series carry - remains underexplored. We address this gap through a benchmark evaluating synthetic generation methods and noise-based anonymization baselines under a Train on Synthetic, Test on Real (TSTR) protocol. We jointly assess forecasting performance and distance-based empirical privacy risk across seven datasets, characterizing the trade-off between these objectives. We also introduce Grasynda-P, a privacy-motivated extension of the graph-based generator Grasynda, incorporating matrix ensembling and kernel density estimation. Our results show that: (1) no generation method fully substitutes for original training data; (2) noise-based anonymization yields the strongest privacy but the worst forecasting performance; (3) simple transformation-based generators outperform deep generative models for forecasting in this setting; and (4) Grasynda-P lies on the Pareto frontier, achieving competitive forecasting with stronger privacy separation than other generators. This benchmark establishes a reference point for evaluating and developing new privacy-aware synthetic time series generation methods.

Related papers

• Privacy Evaluation of Generative Models for Trajectory Generation [0.3998450019209938]
  Traversay data is fundamental to modern urban intelligence, yet its sensitivity raises privacy concerns.<n>We investigate intersection of generative trajectory modeling and privacy evaluation.
  arXiv  Detail & Related papers  (2026-05-14T10:57:34Z)
• Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition [60.52810518437911]
  High-fidelity generative models are increasingly needed in privacy-sensitive scenarios.<n> limited data leads to poor generative models, which in turn fail to mitigate data scarcity.<n>We propose a reinforcement-guided synthetic data generation framework that adapts general-domain generative priors to identity recognition tasks.
  arXiv  Detail & Related papers  (2026-04-09T06:52:03Z)
• SynDelay: A Synthetic Dataset for Delivery Delay Prediction [50.56729406793283]
  We present SynDelay, a synthetic dataset designed for delivery delay prediction.<n>It is publicly available through the Supply Chain Data Hub, an open initiative promoting dataset sharing and benchmarking in supply chain AI.
  arXiv  Detail & Related papers  (2025-08-30T21:54:37Z)
• Latent Noise Injection for Private and Statistically Aligned Synthetic Data Generation [7.240170769827935]
  Synthetic data generation has become essential for scalable, privacy-preserving statistical analysis.<n>We propose a Latent Noise Injection method using Masked Autoregressive Flows (MAF)<n>Instead of directly sampling from the trained model, our method perturbs each data point in the latent space and maps it back to the data domain.
  arXiv  Detail & Related papers  (2025-06-19T22:22:57Z)
• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training [10.229653770070202]
  Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. We consider the slicing privacy mechanism that injects noise into random low-dimensional projections of the private data. We present a kernel-based estimator for this divergence, circumventing the need for adversarial training.
  arXiv  Detail & Related papers  (2024-10-25T19:32:58Z)
• Synthesizing Multimodal Electronic Health Records via Predictive Diffusion Models [69.06149482021071]
  We propose a novel EHR data generation model called EHRPD. It is a diffusion-based model designed to predict the next visit based on the current one while also incorporating time interval estimation. We conduct experiments on two public datasets and evaluate EHRPD from fidelity, privacy, and utility perspectives.
  arXiv  Detail & Related papers  (2024-06-20T02:20:23Z)
• ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generation [19.18074489351738]
  We propose a Graph-based model for generating privacy-protected data. Experiments conducted on three real-worldtemporal datasets validate the efficacy of our model. The prediction model trained on our generated data maintains a competitive edge compared to the model trained on the original data.
  arXiv  Detail & Related papers  (2024-06-04T04:43:54Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Hide-and-Seek Privacy Challenge [88.49671206936259]
  The NeurIPS 2020 Hide-and-Seek Privacy Challenge is a novel two-tracked competition to accelerate progress in tackling both problems. In our head-to-head format, participants in the synthetic data generation track (i.e. "hiders") and the patient re-identification track (i.e. "seekers") are directly pitted against each other by way of a new, high-quality intensive care time-series dataset.
  arXiv  Detail & Related papers  (2020-07-23T15:50:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.