TY - GEN
T1 - Over-the-Air Federated Learning with Enhanced Privacy
AU - Xue, Xiaochan
AU - Hasan, Moh Khalid
AU - Yu, Shucheng
AU - Kandel, Laxima Niure
AU - Song, Min
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Federated learning (FL) has emerged as a promising learning paradigm in which only local model parameters (gradients) are shared. Private user data never leaves the local devices thus preserving data privacy. However, recent research has shown that even when local data is never shared by a user, exchanging model parameters without protection can also leak private information. Moreover, in wireless systems, the frequent transmission of model parameters can cause tremendous bandwidth consumption and network congestion when the model is large. To address this problem, we propose a new FL framework with efficient over-the-air parameter aggregation and strong privacy protection of both user data and models. We achieve this by introducing pairwise cancellable random artificial noises (PCR-ANs) on end devices. As compared to existing over-the-air computation (AirComp) based FL schemes, our design provides stronger privacy protection. We analytically show the secrecy capacity and the convergence rate of the proposed wireless FL aggregation algorithm.
AB - Federated learning (FL) has emerged as a promising learning paradigm in which only local model parameters (gradients) are shared. Private user data never leaves the local devices thus preserving data privacy. However, recent research has shown that even when local data is never shared by a user, exchanging model parameters without protection can also leak private information. Moreover, in wireless systems, the frequent transmission of model parameters can cause tremendous bandwidth consumption and network congestion when the model is large. To address this problem, we propose a new FL framework with efficient over-the-air parameter aggregation and strong privacy protection of both user data and models. We achieve this by introducing pairwise cancellable random artificial noises (PCR-ANs) on end devices. As compared to existing over-the-air computation (AirComp) based FL schemes, our design provides stronger privacy protection. We analytically show the secrecy capacity and the convergence rate of the proposed wireless FL aggregation algorithm.
KW - Over-the-air computation (AirComp)
KW - federated learning
KW - wireless multiple-access channel
UR - http://www.scopus.com/inward/record.url?scp=85178317512&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85178317512&partnerID=8YFLogxK
U2 - 10.1109/ICC45041.2023.10278765
DO - 10.1109/ICC45041.2023.10278765
M3 - Conference contribution
AN - SCOPUS:85178317512
T3 - IEEE International Conference on Communications
SP - 4546
EP - 4551
BT - ICC 2023 - IEEE International Conference on Communications
A2 - Zorzi, Michele
A2 - Tao, Meixia
A2 - Saad, Walid
T2 - 2023 IEEE International Conference on Communications, ICC 2023
Y2 - 28 May 2023 through 1 June 2023
ER -