Hybrid Framework for Intrusion Detection System using Ensemble Approach
Shraddha R. Khonde · International Journal of Advanced Trends in Computer Science and Engineering · 2020
Malicious attack detection is a new emerging area of research now days due to huge number of internet and network usage.Attack detection in network is handled by a system called Intrusion Detection System (IDS).Most of the administrators make use of IDS for monitoring malicious activities of the network.To increase attack detection rate for securing network IDS need to work intelligently.Various machine learning algorithms are used to improve IDS performance considering threat of attacks in modern era of internet.In this paper a novel framework is proposed which will make use of signature as well as anomaly based detection to increase detection rate and reduce false alarm rate.This architecture makes use of various supervised and unsupervised machine learning algorithms for testing real time internet traffic.Dataset used for testing proposed framework is Intrusion Detection Evaluation Dataset CICIDS-17.This framework emphasis of attack detection using signature based detection and propose a new method for new attack detection using anomaly based identification.Dataset used for training deals with various modern attacks and helps to find signature of new attack with help of 88 features of dataset.Various feature selection techniques are used to reduce number of features from dataset to reduce computation time of the system.As this framework is proposed for distributed networks feature selection plays a vital role in performance of system.An experiment results shows that proposed architecture which makes use of ensemble approach provides better performance in terms of detection rate and false alarm rate.Proposed architecture shows increase in detection rate by 5% for signature based detection and 2% for anomaly based detection.Reduction of 0.05 is observed in false alarm rate.