DePoL: Assuring training integrity in collaborative learning via decentralized verification

• Published in: Journal of parallel and distributed computing Vol. 199; p. 105056
• Main Authors: Xu, Zhicheng, Zhang, Xiaoli, Yin, Xuanyu, Cheng, Hongbing
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.05.2025
• Subjects: Collaborative learning; Distributed systems; Proof of learning; Scalability; Training integrity; Scalability; Proof of learning; Distributed systems; Collaborative learning; Training integrity

Collaborative learning enables multiple participants to jointly train complex models but is vulnerable to attacks like model poisoning or backdoor attacks. Ensuring training integrity can prevent these threats by blocking any tampered contributions from affecting the model. However, traditional appr...