Campus Network Intrusion Detection based on Federated Learning

Junjun Chen, Qiang Guo, Zhongnan Fu, Qun Shang, Hao Ma, Di Wu

Abstract: To solve the problem of data scarcity and data silos in campus network intrusion detection, an intrusion detection method based on federated learning is proposed. This method allows multiple participants to collaboratively train a global detection model without sharing their training data with third parties, protecting data privacy. Federated learning is connected to transfer learning, as federated learning allows participants' knowledge transfer via its training mechanism. The resampling method is used in the federated learning training process to improve the global detection model's performance on rare class data. Besides, a contribution evaluation method is proposed, which evaluates participants' contribution in federated learning from two aspects of data quality and quantity. Experimental results show that the proposed method can achieve intrusion detection performance similar to traditional centralized collaborative learning under the premise of protecting participant data privacy.