• Maddika Taruneshwar Reddy
• Kommireddy Nagarjuna Reddy
• Kota Jagan Mohan Reddy
• Kasireddy Venkata Harinadhreddy
• G. Vimal Subramanian

The ability of the Support Vector Machine (SVM) and Artificial Neural Networks (ANN) supervised machine learning algorithms to detect attack (anomaly) signatures in request data was studied in this study. All services are accessible online, allowing malicious users to attack client or server machines through the network. To prevent these attacks, Intrusion Detection Systems (IDS) examine incoming requests for legitimate or malicious signatures and refuse the latter. By applying machine learning techniques, the IDS can learn about all possible attack signatures and create a model that can be used to assess any new request signature. The IDS must initially be taught all likely attack scenarios before categorizing or classifying data using a range of data mining techniques. The paper author analyzed and contrasted the performance of SVM and ANN and used Chi-Square and correlation-based feature selection methods to reduce the dataset's size, boosting prediction accuracy by deleting superfluous data and concentrating on crucial features. Examples of request signature records may be found in the "dataset" folder, which was used for experimenting with the NSL KDD dataset.

Leveraging Supervised Machine Learning To Diagnose Network Invasion Predicated On Feature Selection

"Leveraging Supervised Machine Learning To Diagnose Network Invasion Predicated On Feature Selection ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.89-94, June-2023, Available :http://www.jetir.org/papers/JETIRFZ06015.pdf

"Leveraging Supervised Machine Learning To Diagnose Network Invasion Predicated On Feature Selection ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. pp89-94, June-2023, Available at : http://www.jetir.org/papers/JETIRFZ06015.pdf