Federated learning for network attack detection using attention-based graph neural networks

• Published in: Scientific reports Vol. 14; no. 1; pp. 19088 - 16
• Main Authors: Jianping, Wu, Guangqiu, Qiu, Chunming, Wu, Weiwei, Jiang, Jiahe, Jin
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 17.08.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 704/172/169/895; 704/844/4081; Accuracy; Collaboration; Data integrity; Deep learning; Graphs; Humanities and Social Sciences; Information technology; Intrusion detection systems; Laboratories; Language; Large language models; Machine learning; multidisciplinary; Neural networks; Privacy; Science; Science (multidisciplinary)

Federated Learning is an effective solution to address the issues of data isolation and privacy leakage in machine learning. However, ensuring the security of network devices and architectures deploying federated learning remains a challenge due to network attacks. This paper proposes an attention-b...