• Bharat Bhushan Mahor
• Pratima Gautam

Popular technologies such as cloud computing the Internet of Things and social networking produce vast volumes of network traffic and data. Intrusion detection systems are therefore essential to track the network and dynamically analyze the incoming traffic. The goal of the intrusion detection system (IDS) is to carry out attack control & to provide desired system security support with intrusion details. The numerous approaches to intrusion detection to predict malicious network traffic have been proposed to date. This paper uses NSLKDD to test intrusion detection machine learning algorithms. Our work aims to examine the theoretical viability of ELM by evaluating the advantages and benefits of ELM. In the last section, we pointed out that the ELM does not degrade the generalization capacity in the expected sense with the proper selection of the activation function. In this study, we begin the analysis in a different direction and demonstrate that random ELM also has some adverse effects. Therefore, by using the Extreme Gradient Boosting Technique we have employed a new technique for machine learning to solve ELM problems.

Network security, IDS, traffic classification, Intrusion Detection, Malicious traffic, Network

"A Network Intrusion Detection System based on Extreme Gradient Boosting Technique ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.2067-2070, April-2019, Available :http://www.jetir.org/papers/JETIR1904S98.pdf

"A Network Intrusion Detection System based on Extreme Gradient Boosting Technique ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp2067-2070, April-2019, Available at : http://www.jetir.org/papers/JETIR1904S98.pdf