• Ruchi Singh
• Mr. Chhatrapani Gautam

Random harmful actions for a single machine or for the whole network may be seen on the internet from time to time. As computer connection continues to expand at an unprecedented rate, it is becoming more difficult to keep up. Security risks may be seen on the internet, just as they can be seen in person. The intrusion detection system (IDS) is designed to identify and investigate such hostile actions occurring across a network. The intrusion detection system (IDS) aids in the detection of assaults on the system and the identification of attackers. Various machine learning (ML) methods have been used to intrusion detection systems in the past, with the goal of improving the results for intruder detection and increasing the accuracy of the IDS. In this article, we present a method for developing an efficient IDS that makes use of the principle component analysis (PCA) and the CNN classification algorithm. PCA may be used to organise data by decreasing its dimensionality, whereas random forest can be used to classify data. The tests will be carried out using the suggested system over the KDD (Knowledge Discovery Dataset). When compared to other methods such as SVM, Naive Bayes, and Decision Tree, it is certain that the suggested methodology would perform more efficiently in terms of accuracy. We got the following findings using our suggested method: performance time (min) is 3.24 minutes, accuracy rate (percentage) is 96.78 percent, and error rate (percentage) is 0.21 percent.

IDS, Knowledge Discovery Dataset, PCA, Random Forest.

"Intrusion Detection System using Machine Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 9, page no.e342-e345, September-2021, Available :http://www.jetir.org/papers/JETIR2109440.pdf

"Intrusion Detection System using Machine Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 9, page no. ppe342-e345, September-2021, Available at : http://www.jetir.org/papers/JETIR2109440.pdf