Research of Intrusion Detection Method Based on IL-FSVM
Dong YuanTong · 2019
Aiming at the problem that the traditional network intrusion detection algorithm has high learning time cost and low recognition accuracy for massive training data, the paper proposes an intrusion detection method based on incremental learning and FSVM(IL-FSVM). This method uses FSVM as the training and classification algorithm for intrusion detection, which reduces the impact of noise samples on intrusion detection and recognition. Based on FSVM, it introduces incremental learning to improve the learning efficiency of massive samples and reduce the learning time cost of the algorithm. The simulation results show that compared with the traditional SVM algorithm, the proposed algorithm can greatly reduce the training time and improve the learning efficiency of the intrusion detection algorithm on the premise of ensuring higher classification accuracy.