AI based intrusion detection system to secure, safeguard and strategize the digital fortress
Kartik Malik, Piyush Gupta, Akshat, Shobha Tyagi, Pronika Chawla · 2024
In today&s;s ever-evolving landscape of cybersecurity, the importance of Intrusion Detection Systems () cannot be overstated, as they serve as a crucial line of defense for our digital environments. This paper introduces a comprehensive exploration of ten distinct machine learning approaches. The objective of this research is to enhance the efficiency of network intrusion detection. To evaluate the effectiveness of these machine learning approaches, we employ the NSL-KDD dataset. This dataset represents a refined version of the widely recognized KDDCup 1999 intrusion detection benchmark dataset. The outcome of proposed research and study is a set of experimental results derived from a 5-class classification, encompassing key metrics such as the detection rate, false positive rate, and the average cost associated with. These results provide valuable insights, contributing to a deeper understanding of network intrusion detection systems for researchers in this field.