PART-GAN: privacy-preserving time-series sharing

Shuo Wang, Carsten Rudolph, Surya Nepal, Marthie Grobler, Shangyu Chen

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

In this paper, we provide a practical privacy-preserving generative model for time series data augmentation and sharing, called PART-GAN. Our model enables the local data curator to provide a freely accessible public generative model derived from original data for cloud storage. Compared with existing approaches, PART-GAN has three key advantages: It enables the generation of an unlimited amount of synthetic time series data under the guidance of a given classification label and addresses the incomplete and temporal irregularity issues. It provides a robust privacy guarantee that satisfies differential privacy to time series data augmentation and sharing. It addresses the trade-offs between utility and privacy by applying optimization strategies. We evaluate and report the utility and efficacy of PART-GAN through extensive empirical evaluations of real-world health/medical datasets. Even at a higher level of privacy protection, our method outperforms GAN with ordinary perturbation. It achieves similar performance with GAN without perturbation in terms of inception score, machine learning score similarity, and distance-based evaluations.

Original languageEnglish
Title of host publicationArtificial Neural Networks and Machine Learning – ICANN 2020
Subtitle of host publication29th International Conference on Artificial Neural Networks Bratislava, Slovakia, September 15–18, 2020 Proceedings, Part I
EditorsIgor Farkaš, Paolo Masulli, Stefan Wermter
Place of PublicationCham Switzerland
PublisherSpringer
Pages578-593
Number of pages16
ISBN (Print)9783030616083
DOIs
Publication statusPublished - 2020
EventInternational Conference on Artificial Neural Networks 2020 - Bratislava, Slovakia
Duration: 15 Sep 202018 Sep 2020
Conference number: 29th
https://link.springer.com/chapter/10.1007%2F978-3-030-61609-0_46 (Proceedings)
https://e-nns.org/icann2020/ (Website)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume12396
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference on Artificial Neural Networks 2020
Abbreviated titleICANN 2020
CountrySlovakia
CityBratislava
Period15/09/2018/09/20
Internet address

Keywords

  • Data sharing
  • Deep learning
  • Differential privacy
  • Generative model
  • Privacy-preserving

Cite this