Intrusion Detection Method Based on Support Vector Machine and Information Gain for Mobile Cloud Computing

Emmanuel Mugabo ； Qiu-Yu Zhang

《International Journal of Network Security》 22卷2期 (2020/03) Pp. 231-241

https://doi.org/10.6633/IJNS.202003_22(2).06

摘要

Intrusion detection system (IDS) has become an important security method that monitors and investigates the network security in mobile cloud computing (MCC). However, in some existing methods, there are still some limitations such as high false positive rates, low classification accuracies, and low true positive rates. To counter these limitations, an intrusion detection method based on support vector machine (SVM) and information gain (IG) for MCC was proposed in this paper. In the proposed method, the SVM classifier is adopted to classify network data into normal and attack behaviors, and due to the irrelevant and redundant features found in KDD datasets, IG is used to select the relevant features and remove unnecessary features. The KDD'99 and NSL-KDD datasets are used to evaluate the effectiveness of the proposed method. Compared with other methods, the experimental results show that the proposed method can detect malicious attacks with high accuracy, true positive rate, low false positive rate and high training speed.

關鍵字

Intrusion Detection ； Information Gain ； Malicious Attacks ； Mobile Cloud Computing ； Support Vector Machine