FLORAS: Differentially Private Wireless Federated Learning Using Orthogonal Sequences

Xizixiang Wei, Tianhao Wang, Ruiquan Huang, Cong Shen, Jing Yang, H. Vincent Poor

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We propose a novel private-preserving uplink over-the-air computation (AirComp) method, termed FLORAS, for wireless federated learning (FL) systems. From the communication design perspective, FLORAS eliminates the requirement of channel state information at the transmitters (CSIT) by leveraging the properties of orthogonal sequences. From the privacy perspective, we prove that FLORAS can offer pure differential privacy (DP) guarantee, and explicitly characterize the achievable ϵ-DP level as a function of the FLORAS parameter configuration. A novel FL convergence bound is derived which, combined with the pure DP guarantee, allows for a smooth tradeoff between convergence rate and DP guarantee levels. Experiments based on real-world datasets not only corroborate the theoretical findings but also empirically demonstrate the communication and privacy advantages of FLORAS over state-of-the-art AirComp methods.

Original languageEnglish (US)
Title of host publicationICC 2023 - IEEE International Conference on Communications
Subtitle of host publicationSustainable Communications for Renaissance
EditorsMichele Zorzi, Meixia Tao, Walid Saad
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781538674628
StatePublished - 2023
Externally publishedYes
Event2023 IEEE International Conference on Communications, ICC 2023 - Rome, Italy
Duration: May 28 2023Jun 1 2023

Publication series

NameIEEE International Conference on Communications
ISSN (Print)1550-3607


Conference2023 IEEE International Conference on Communications, ICC 2023

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering


  • Code-division multiple access (CDMA)
  • Differential privacy (DP)
  • Federated learning
  • Orthogonal sequence


Dive into the research topics of 'FLORAS: Differentially Private Wireless Federated Learning Using Orthogonal Sequences'. Together they form a unique fingerprint.

Cite this