Verifiable secure aggregation scheme for privacy protection in federated learning networks

• Published in: Discover Computing Vol. 28; no. 1; pp. 175 - 30
• Main Authors: Yao, Wujun, Zhou, Tanping, Han, Yiliang, Wang, Xiaolin
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.12.2025; Springer Nature B.V; Springer
• Subjects: Clients; Collaboration; Communication; Computer Science; Cryptography; Data Mining and Knowledge Discovery; Data Structures and Information Theory; Edge computing; Efficiency; Federated learning; Forgery; Information Storage and Retrieval; Integrity; Machine learning; Natural Language Processing (NLP); Pattern Recognition; Privacy; Privacy protection; Servers; Signal processing; Verifiable aggregation; Verification; Privacy protection; Federated learning; Verifiable aggregation; Edge computing

Federated learning enables multiple participants to construct a distributed machine learning system coordinated by a server. Most existing solutions assume a semi-honest system, considering each participant to be honest but curious, which does not align with the complex real-world environment. In re...