Network Intrusion Detection using Supervised Machine Learning Algorithms a Comprehensive Evaluation

K Nagamani1
Department of Computer Science and Engineering
Sri Venkateswara College of
Engineering,Karakambadi
Tirupati, India, 517509
manibalu013@gmail.com

Saritha A2
Department of Computer Science and Engineering
Sri Venkateswara College of Engineering,
Karakambadi
Tirupati, India, 517509
saritha.a@svcolleges.edu.in

Abstract:The rapid expansion of internet-based services has significantly increased global connectivity while simultaneously exposing network systems to advancedcyber threats. To address these challenges, NetworkIntrusion Detection Systems (NIDS) have emerged as  intelligent, machine learning–based solutions for real-me monitoring and protection of network traffic. Thesesystems are trained on large datasets containing both  normal and malicious activity patterns to build predictive models capable of identifying potential attacks. However,the effectiveness of such systems depends on the accuracy and efficiency of the underlying algorithms. This study focuses on comparing two widely used supervised learning techniques, Support Vector Machines (SVM) and Artificial Neural Networks (ANN), to enhance intrusion detection performance. By evaluating their classification capabilities, the study demonstrates that ANN provides superior accuracy and more robust threat detection, thereby improving the reliability and effectiveness of modern cybersecurity systems.
Keywords:Network Intrusion Detection System (NIDS),cybersecurity, machine learning, Support Vector Machine (SVM), Artificial Neural Network (ANN), anomaly detection, network security, real-time monitoring, attack detection, predictive modeling, data-driven security.