A Hybrid Intrusion Detection Method Based on Improved Fuzzy C-Means and Support Vector Machine
Zhiyou Zhang, Peisheng Pan · 2019
Currently, Intrusion Detection System (IDS) is an essential component of network security, which can detect abnormal access data or attacks. Misuse detection or anomaly detection is generally adopted in most of the existing IDS, while there are some disadvantages such as low detection rate and high false alarm rate. In this paper, a hybrid intrusion detection method based on improved Fuzzy C-Means (FCM) and Support Vector Machine (SVM) has been proposed. In the new method, FCM incorporating information gain ratio is firstly used to cluster the pre-processed training dataset, then SVM is used to classify them. The NSL-KDD dataset is used to verify the feasibility of the method. Accuracy, detection rate, and false alarm rate are indicators to evaluate its performance. The experimental results demonstrate that compared with other intrusion detection methods, the proposed method can detect intrusion attacks more effectively and decrease the false alarm rate.