Ensemble Based Intrusion Detection System for Multi attack Environment
Satyapriya S. Raut, Aniketh R. Poojary, Aditya C. Naiknaware, Sushant G. Vairat, Prof. Shraddha R. Khonde
Ensemble, Intrusion Detection System, Machine Learning, XGBoost, Random Forest, Extra Tree, Bagging, Boosting, Stacking, NSL-KDD.
Due to mass usage of Internet in today’s era, cyber-attacks have been very common. These pose a serious threat to the organization as well as for an individual. The sensitive and confidential data that needs to be protected is at high risk and is stolen by attackers using various types of attacks. In multi attack environment, there would be more than one attack occurring simultaneously or within a short span of time. In our project, we have considered all those attacks as multi attacks which occur within one second of time span. We have proposed a system that captures live packets from the network and classifies whether the packet is normal or belongs to one of the subclasses of attack using various ensemble approaches such as Bagging, Boosting and Stacking. NSL-KDD dataset has been used for both training and testing the model. We found out that XGBoost outperforms with highest accuracy, 72.27%, followed by Random Forest classifier, 72.22%.