TY - GEN
T1 - Differential Privacy in HyperNetworks for Personalized Federated Learning
AU - Nemala, Vaisnavi
AU - Lai, Phung
AU - Phan, Nhat Hai
N1 - Publisher Copyright:
© 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.
PY - 2023/10/21
Y1 - 2023/10/21
N2 - Federated learning (FL) is a framework for collaborative learning among users through a coordinating server. A recent HyperNetwork-based personalized FL framework, called HyperNetFL, is used to generate local models using personalized descriptors optimized for each user independently. However, HyperNetFL introduces unknown privacy risks. This paper introduces a novel approach to preserve user-level differential privacy, dubbed User-level DP, by providing formal privacy protection for data owners in training a HyperNetFL model. To achieve that, our proposed algorithm, called UDP-Alg, optimizes the trade-off between privacy loss and model utility by tightening sensitivity bounds. An intensive evaluation using benchmark datasets shows that our proposed UDP-Alg significantly improves privacy protection at a modest cost in utility.
AB - Federated learning (FL) is a framework for collaborative learning among users through a coordinating server. A recent HyperNetwork-based personalized FL framework, called HyperNetFL, is used to generate local models using personalized descriptors optimized for each user independently. However, HyperNetFL introduces unknown privacy risks. This paper introduces a novel approach to preserve user-level differential privacy, dubbed User-level DP, by providing formal privacy protection for data owners in training a HyperNetFL model. To achieve that, our proposed algorithm, called UDP-Alg, optimizes the trade-off between privacy loss and model utility by tightening sensitivity bounds. An intensive evaluation using benchmark datasets shows that our proposed UDP-Alg significantly improves privacy protection at a modest cost in utility.
KW - Differential Privacy
KW - Federated Learning
KW - Hypernetworks
UR - http://www.scopus.com/inward/record.url?scp=85178152945&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85178152945&partnerID=8YFLogxK
U2 - 10.1145/3583780.3615203
DO - 10.1145/3583780.3615203
M3 - Conference contribution
AN - SCOPUS:85178152945
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 4224
EP - 4228
BT - CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
Y2 - 21 October 2023 through 25 October 2023
ER -