Senspy: An Integrated Network Monitoring and Anomaly Detection System Using Machine Learning
Bandaru Jnyanadeep, Nikunj Mittal, P N Srivishnu, Y Varshith, Mohana, Minal Moharir, Ashok Kumar A R · 2024
In the evolving cybersecurity landscape, the surge in cyber threats necessitates innovative defence mechanisms. Proposed work explores the integration of ML methods into Intrusion Detection System (IDS) Senspy tool. Senspy, an adaptive IDS software incorporates ML techniques like k-Nearest Neighbors (KNN), Random Forest and Logistic Regression, to enhance its detection capabilities of cyber threats. It's beneficial for recognizing outliers or unusual patterns in network traffic. By employing ML techniques, Senspy excels in detecting and identifying various cyber-attacks, surpassing traditional IDS capabilities. The system demonstrates robust performance, particularly with Random Forest algorithm achieving over accuracy and an F1 score of 99.6%.