FEDERATED LEARNING WITH DYNAMIC TRUST SCORING FOR UNRELIABLE OR ADVERSARIAL NODES
Keywords:
Federated Learning, Trust Scoring, Byzantine Attacks, Distributed Machine Learning, Model Aggregation, Adversarial Robustness, Node ReliabilityAbstract
Federated learning enables collaborative machine learning across distributed devices whilepreserving data privacy, yet it remains vulnerable to unreliable participants and maliciousadversaries who can compromise model integrity. This research addresses the critical challenge of maintaining model quality when some participating nodes
References
Anderson, K., Roberts, M. and Thompson, D. (2023) 'Anomaly detection in distributed machine learning: Statistical approaches and practical considerations', IEEE Transactions on Neural Networks and Learning Systems, 34(5), pp. 2341-2365.
Downloads
Published
2024-09-20
How to Cite
Dr. T. Prem Chander,Dr. B.K Sarkar [Patent Guru]. (2024). FEDERATED LEARNING WITH DYNAMIC TRUST SCORING FOR UNRELIABLE OR ADVERSARIAL NODES . Journal of Computational Analysis and Applications (JoCAAA), 33(08), 2935–2952. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/4573
Issue
Section
Articles
