EUVIMEDEUVIMED entdecken
Crossref

Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks

Caridad Arroyo Arevalo, Sayedeh Leila Noorbakhsh, Yun Dong, Yuan Hong, Binghui Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (10) · 10909-10917

DOI: 10.1609/aaai.v38i10.28965 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Caridad Arroyo Arevalo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) has been widely studied recently due to its property to collaboratively train data from different devices without sharing the raw data. Nevertheless, recent studies show that an adversary can still be possible to infer private information about devices' data, e.g., sensitive attributes such as income, race, and sexual orientation. To mitigate the attribute inference attacks, various existing privacy-preserving FL methods can be adopted/adapted. However, all these existing methods have key limitations: they need to know the FL task in advance, or have intolerable computational overheads or utility losses, or do not have provable privacy guarantees. We address these issues and design a task-agnostic privacy-preserving presentation learning method for FL (TAPPFL) against attribute inference attacks. TAPPFL is formulated via information theory. Specifically, TAPPFL has two mutual information goals, where one goal learns task-agnostic data representations that contain the least information about the private attribute in each device's data, and the other goal ensures the learnt data representations include as much information as possible about the device data to maintain FL utility. We also derive privacy guarantees of TAPPFL against worst-case attribute inference attacks, as well as the inherent tradeoff between utility preservation and privacy protection. Extensive results on multiple datasets and applications validate the effectiveness of TAPPFL to protect data privacy, maintain the FL utility, and be efficient as well. Experimental results also show that TAPPFL outperforms the existing defenses.

Zitieren

APA

Arevalo, C. A., Noorbakhsh, S. L., Dong, Y., Hong, Y., & Wang, B. (2024). Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, 38(10), 10909-10917. https://doi.org/10.1609/aaai.v38i10.28965

Vancouver

Arevalo CA, Noorbakhsh SL, Dong Y, Hong Y, Wang B. Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(10):10909-10917. doi:10.1609/aaai.v38i10.28965

BibTeX
@article{Arevalo2024,
  author = {Arevalo, Caridad Arroyo and Noorbakhsh, Sayedeh Leila and Dong, Yun and Hong, Yuan and Wang, Binghui},
  title = {Task-Agnostic Privacy-Preserving Representation Learning for Federated Learning against Attribute Inference Attacks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {10},
  pages = {10909--10917},
  doi = {10.1609/aaai.v38i10.28965}
}
Kostenlos starten →