Federated Learning with Real-world Datasets: Compliance with the Privacy Act

Paper


Tang, Zhaohui and Keoh, Sye Loong. 2022. "Federated Learning with Real-world Datasets: Compliance with the Privacy Act." Cho, Seongsoo (ed.) 9th International Conference on Advanced Engineering and ICT-Convergence (ICAEIC-2022). Jeju Island, Korea 13 - 15 Jul 2022 Seoul, Korea.
Paper/Presentation Title

Federated Learning with Real-world Datasets: Compliance with the Privacy Act

Presentation TypePaper
AuthorsTang, Zhaohui (Author) and Keoh, Sye Loong (Author)
EditorsCho, Seongsoo
Journal or Proceedings TitleProceedings of the 9th International Conference on Advanced Engineering and ICT-Convergence (ICAEIC-2022)
Journal Citation5 (2), pp. 238-259
Article Number152
Number of Pages22
Year2022
Place of PublicationSeoul, Korea
Web Address (URL) of Paperhttps://ictaes.org/9th-international-conference/conference-program/
Conference/Event9th International Conference on Advanced Engineering and ICT-Convergence (ICAEIC-2022)
Event Details
9th International Conference on Advanced Engineering and ICT-Convergence (ICAEIC-2022)
Event Date
13 to end of 15 Jul 2022
Event Location
Jeju Island, Korea
Abstract

Federated learning has been demonstrated to face challenges when applied into real-world environment whereas data are prone to be not independent and identically distributed (non-IID) and imbalanced. Moreover, despite its privacy-aware paradigm, standard federated learning is vulnerable to privacy attacks where the model parameters exchanged among participants may contain some information that can be exploited to reveal various sensitive information related to participant training data or their properties. With privacy-preserving federated learning proposed to tackle privacy attacks, the challenge of achieving a trade-off between privacy and accuracy has been a concern, particularly, in a real-world privacy-preserving federated learning setting. This paper reviews state-of-the-art federated learning schemes, including both standard and privacy-preserving federated learning schemes, with a focus on those tested with real-world data. Furthermore, we noticed that federated learning-based applications are not naturally compliant with government defined data protection regulations such as the Privacy Act (i.e., the 13 Australian Privacy Principles), which is similar to other machine learning-based applications. In this paper, we investigate the compliance of federated learning against the Privacy Act, including a summary of challenges encountered in terms of complying some of the Australian Privacy Principles (APPs). Recommendations including remedies are suggested for enhancing an FL scheme for complying with all the 13 APPs, that is, the entire Privacy Act.

KeywordsFederated Learning, Privacy-preserving, Privacy Act, Australian Privacy Principles, Real-world Federated Learning Schemes
ANZSRC Field of Research 2020460299. Artificial intelligence not elsewhere classified
460402. Data and information privacy
Public Notes

Files associated with this item cannot be displayed due to copyright restrictions.

Byline AffiliationsUniversity of Southern Queensland
University of Glasgow, United Kingdom
Institution of OriginUniversity of Southern Queensland
Permalink -

https://research.usq.edu.au/item/q7734/federated-learning-with-real-world-datasets-compliance-with-the-privacy-act

  • 112
    total views
  • 6
    total downloads
  • 2
    views this month
  • 0
    downloads this month

Export as

Related outputs

A Review of Homomorphic Encryption for Privacy-Preserving Biometrics
Yang, Wencheng, Wang, Song, Cui, Hui, Tang, Zhaohui and Li, Yan. 2023. "A Review of Homomorphic Encryption for Privacy-Preserving Biometrics." Sensors. 23 (7). https://doi.org/10.3390/s23073566
Efficient Beaver Triple Generation for Privacy-preserving Collaborative Machine Learning
Tang, Zhaohui. 2022. "Efficient Beaver Triple Generation for Privacy-preserving Collaborative Machine Learning." Cho, Seongsoo (ed.) 9th International Conference on Advanced Engineering and ICT-Convergence (ICAEIC-2022). Jeju Island, Korea 13 - 15 Jul 2022 Seoul, Korea.
Secret sharing-based IoT text data outsourcing: a secure and efficient scheme
Tang, Zhaohui. 2021. "Secret sharing-based IoT text data outsourcing: a secure and efficient scheme." IEEE Access. 9, pp. 76908 -76920. https://doi.org/10.1109/ACCESS.2021.3075282
An Efficient Scheme to Secure Data Provenance in Home Area Networks
Tang, Zhaohui and Keoh, Sye Loong. 2020. "An Efficient Scheme to Secure Data Provenance in Home Area Networks." IEEE 3rd 5G World Forum (5GWF 2020). Bangalore, India 10 - 12 Sep 2020 United States. https://doi.org/10.1109/5GWF49715.2020.9221402
Privacy Preserving Computation in Home Loans Using the FRESCO Framework
Chan, Fook Mun, Xu, Quanqing, Seah, Hao Jian, Keoh, Sye Loong, Tang, Zhaohui and Aung, Khin Mi Mi. 2019. "Privacy Preserving Computation in Home Loans Using the FRESCO Framework." Kacprzyk, Janusz (ed.) 2018 Future of Information and Communication Conference (FICC 2018). Singapore 05 - 06 Apr 2018 Switzerland. https://doi.org/10.1007/978-3-030-03405-4_7
Authentication and Integrity Protection for Real-time Cyber-Physical Systems
Keoh, Sye Loong, Tan, Heng Chuan and Tang, Zhaohui. 2020. "Authentication and Integrity Protection for Real-time Cyber-Physical Systems." Tian, Yu-Chu and Levy, David Charles (ed.) Handbook of Real-Time Computing. Singapore. Springer. pp. 1-22