Anomaly Detection Using Supervised learning Techniques in Social Networks

Abstract

Intrusion detection corresponds to a suite of techniques that are used to identify attacks against computers and network infrastructures. As the cost of the information processing and Internet accessibility falls, more and more organizations are becoming vulnerable to a wide variety of cyber threats. Web mining based intrusion detection techniques generally fall into one of two categories; misuse detection and anomaly detection. In misuse detection, each instance in a data set is labelled as ‘normal’ or ‘intrusive’ and a learning algorithm is trained over the labelled data. These techniques are able to automatically retrain intrusion detection models on different input data that include new types of attacks, as long as they have been labelled appropriately. Evaluation results show that the proposed approach can reduce the number of alerts by 94.32%, effectively improving alert management process. Because of the use of ensemble approach and optimal algorithms in the proposed approach, it can inform network security specialist the state of the monitored network in an online manner.