Design of intrusion detection system to detect black hole attack using random forest technique in wireless ad hoc network comparing with decision tree algorithm
Amulya Korsapati, T. J. Nagalakshmi · AIP conference proceedings · 2024
Aim: The aim of the work is to design two intrusion detection systems to detect black hole attack in the wireless ad-hoc network using the Random Forest technique (Group 1) and Decision tree algorithm (Group 2).Then to compare its performance metrics.Materials and Methods: In a wireless ad-hoc network, a dataset is generated with 90 nodes and 12 network layer features in NS-2.Above mentioned intrusion detection systems are developed and analyzed by using the SPSS.For each group 19 samples were collected.The significance 0.006 (p<0.05)indicates the performance of IDS.Results: IDS using Random Forest algorithm achieved accuracy and detection rate of 99.4% and 99.1% respectively.And 99.5% and 97.3% for IDS with decision tree algorithms.Conclusion: In this study, it is found that the random forest algorithm significantly performs better when compared with the decision tree algorithm in the detection of black hole attack.