An Efficient Intrusion Detection Method Based on Federated Transfer Learning

With the popularity of the Internet, network security is becoming more and more important in real life. This paper proposed a new intrusion detection algorithm FETLSVM to protect network security against network intrusion. Under the federation learning framework, FETLSVM constructs a transfer learning model based on support vector theory and transfer learning using intrusion detection data distributed in various organizations. The experimental verification of the algorithm on intrusion detection data CICIDS2017.