Work place: Department of Computer Science & Engineering, G H Raisoni College of Engineering, Nagpur, India
Research Interests: Network Security
Dr. Prasad P. Lokulwar is employed as an Associate Professor at G H Raisoni College of Engineering, Nagpur, Maharashtra His PhD in Computer Science & Engineering was granted by SGBAU Amravati University in Amravati. Additionally, he is responsible for more than 25 research papers that have been published in major national and international journals and conferences. His interests lie in the fields of network security and the internet of things.
DOI: https://doi.org/10.5815/ijcnis.2023.03.03, Pub. Date: 8 Jun. 2023
Over the last two years,the number of cyberattacks has grown significantly, paralleling the emergence of new attack types as intruder’s skill sets have improved. It is possible to attack other devices on a botnet and launch a man-in-the-middle attack with an IOT device that is present in the home network. As time passes, an ever-increasing number of devices are added to a network. Such devices will be destroyed completely if one or both of them are disconnected from a network. Detection of intrusions in a network becomes more difficult because of this. In most cases, manual detection and intervention is ineffective or impossible. Consequently, it's vital that numerous types of network threats can be better identified with less computational complexity and time spent on processing. Numerous studies have already taken place, and specific attacks are being examined. In order to quickly detect an attack, an IDS uses a well-trained classification model. In this study, multi-layer perceptron classifier along with random forest is used to examine the accuracy, precision, recall and f-score of IDS. IoT environment-based intrusion related benchmark datasets UNSWNB-15 and N_BaIoT are utilized in the experiment. Both of these datasets are relatively newer than other datasets, which represents the latest attack. Additionally, ensembles of different tree sizes and grid search algorithms are employed to determine the best classifier learning parameters. The research experiment's outcomes demonstrate the effectiveness of the IDS model using random forest over the multi-layer perceptron neural network model since it outperforms comparable ensembles analyzed in the literature in terms of K-fold cross validation techniques.[...] Read more.
Subscribe to receive issue release notifications and newsletters from MECS Press journals