TimeWak: Temporal Chained-Hashing Watermark for Time Series Data
Zhi Wen Soi, Chaoyi Zhu, Fouad Abiad, Aditya Shankar, Jeroen M. Galjaard, Huijuan Wang, Lydia Y. Chen

TL;DR
TimeWak is a novel watermarking method designed for multivariate time series generated by diffusion models, enabling data source verification without compromising data utility or privacy.
Contribution
It introduces the first data-space watermarking algorithm for time series diffusion models, handling temporal dependencies and feature heterogeneity with a novel chained-hashing approach.
Findings
Achieves 61.96% improvement in context-FID score.
Improves correlational scores by 8.44%.
Maintains high detectability under various attacks.
Abstract
Synthetic time series generated by diffusion models enable sharing privacy-sensitive datasets, such as patients' functional MRI records. Key criteria for synthetic data include high data utility and traceability to verify the data source. Recent watermarking methods embed in homogeneous latent spaces, but state-of-the-art time series generators operate in data space, making latent-based watermarking incompatible. This creates the challenge of watermarking directly in data space while handling feature heterogeneity and temporal dependencies. We propose TimeWak, the first watermarking algorithm for multivariate time series diffusion models. To handle temporal dependence and spatial heterogeneity, TimeWak embeds a temporal chained-hashing watermark directly within the temporal-feature data space. The other unique feature is the -exact inversion, which addresses the non-uniform…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsMachine Learning in Healthcare · Advanced Steganography and Watermarking Techniques · Time Series Analysis and Forecasting
MethodsDiffusion
