
Detecting anomalous traffic in the controlled network based on cross entropy and support vector machine
Author(s) -
Han Weijie,
Xue Jingfeng,
Yan Hui
Publication year - 2019
Publication title -
iet information security
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.308
H-Index - 34
eISSN - 1751-8717
pISSN - 1751-8709
DOI - 10.1049/iet-ifs.2018.5186
Subject(s) - support vector machine , computer science , anomaly detection , tuple , entropy (arrow of time) , artificial intelligence , data mining , cross entropy , feature vector , pattern recognition (psychology) , curse of dimensionality , classifier (uml) , machine learning , mathematics , physics , discrete mathematics , quantum mechanics
Network anomaly detection is an effective way for analysing and detecting malicious attacks. However, the typical anomaly detection techniques cannot perform the desired effect in the controlled network just as in the general network. In the circumstance of the controlled network, the detection performance will be lowered due to its special characteristics including the stronger regularity, higher dimensionality and subtler fluctuation of its traffic. On the motivation, the study proposes a novel classifier framework based on cross entropy and support vector machine (SVM). The technique first subtracts the representative traffic characteristics from the network traffic and defines a 7‐tuple feature vector for the controlled network by extending the traditional 5‐tuple representation of the usual network. Then the probability distributions and cross entropies of the 7 tuples are calculated during the defined statistical window so as to generate the 7‐tuple cross‐entropy feature vector for profiling the network traffic fluctuation in the controlled network. Finally, the multi‐class SVM classifier is trained by importing the 7‐tuple cross‐entropy feature vectors. Experimental results show that the proposed classifier can achieve higher detection rates and is more suitable to be used in the controlled network than the typical detection techniques.