EUVIMEDEUVIMED entdecken
Crossref

No Free Lunch Theorem for Security and Utility in Federated Learning

Xiaojin Zhang, Hanlin Gu, Lixin Fan, Kai Chen, Qiang Yang

ACM Transactions on Intelligent Systems and Technology · 28.02.2023 · 14 (1) · 1-35

DOI: 10.1145/3563219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 09.11.2022. Verfasst von Xiaojin Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 90 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Hong Kong RGC.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms. On one hand, private and sensitive training data must be kept secure as much as possible in the presence of semi-honest partners; on the other hand, a certain amount of information has to be exchanged among different parties for the sake of learning utility. Such a challenge calls for the privacy-preserving federated learning solution, which maximizes the utility of the learned model and maintains a provable privacy guarantee of participating parties’ private data. This article illustrates a general framework that (1) formulates the trade-off between privacy loss and utility loss from a unified information-theoretic point of view, and (2) delineates quantitative bounds of the privacy-utility trade-off when different protection mechanisms including randomization, sparsity, and homomorphic encryption are used. It was shown that in general there is no free lunch for the privacy-utility trade-off , and one has to trade the preserving of privacy with a certain degree of degraded utility. The quantitative analysis illustrated in this article may serve as the guidance for the design of practical federated learning algorithms.

Förderung

  • National Key Research and Development Program of China
  • Hong Kong RGC

Zitieren

APA

Zhang, X., Gu, H., Fan, L., Chen, K., & Yang, Q. (2023). No Free Lunch Theorem for Security and Utility in Federated Learning. ACM Transactions on Intelligent Systems and Technology, 14(1), 1-35. https://doi.org/10.1145/3563219

Vancouver

Zhang X, Gu H, Fan L, Chen K, Yang Q. No Free Lunch Theorem for Security and Utility in Federated Learning. ACM Transactions on Intelligent Systems and Technology. 2023;14(1):1-35. doi:10.1145/3563219

BibTeX
@article{Zhang2023,
  author = {Zhang, Xiaojin and Gu, Hanlin and Fan, Lixin and Chen, Kai and Yang, Qiang},
  title = {No Free Lunch Theorem for Security and Utility in Federated Learning},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2023},
  volume = {14},
  number = {1},
  pages = {1--35},
  doi = {10.1145/3563219}
}
Kostenlos starten →