TY - GEN
T1 - Anomaly and Intrusion Detection in Communication Networks using Machine Learning
AU - Deepa,
AU - Kumar, Archana Praveen
AU - Sai Sharath, R. S.
AU - Pathak, Pratham
AU - Kotian, Shreyas B.
AU - Kumar, Rohan
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - Network communication security is the most important factor in today's connected and digitally driven world. With the rapid growth of internet-based services and the increasing dependency on online infrastructure, ensuring the security of communication networks has become more important than ever. As cyberattacks have become more complicated, traditional security measures frequently fall short in identifying and reducing the new threats effectively. This paper focuses on network anomalies, unusual patterns of behavior that may indicate security breaches or malicious activities. It evaluates machine learning techniques for detecting and mitigating modern network security risks. The study explores anomaly and intrusion detection in communication networks using machine learning models like Logistic Regression, Random Forest, and K-Nearest Neighbors. The outcomes suggest that machine learning offers a promising and efficient approach in enhancing real-time threat detection and improves overall defense mechanisms.
AB - Network communication security is the most important factor in today's connected and digitally driven world. With the rapid growth of internet-based services and the increasing dependency on online infrastructure, ensuring the security of communication networks has become more important than ever. As cyberattacks have become more complicated, traditional security measures frequently fall short in identifying and reducing the new threats effectively. This paper focuses on network anomalies, unusual patterns of behavior that may indicate security breaches or malicious activities. It evaluates machine learning techniques for detecting and mitigating modern network security risks. The study explores anomaly and intrusion detection in communication networks using machine learning models like Logistic Regression, Random Forest, and K-Nearest Neighbors. The outcomes suggest that machine learning offers a promising and efficient approach in enhancing real-time threat detection and improves overall defense mechanisms.
UR - https://www.scopus.com/pages/publications/105030342273
UR - https://www.scopus.com/pages/publications/105030342273#tab=citedBy
U2 - 10.1109/ICoICI65217.2025.11253349
DO - 10.1109/ICoICI65217.2025.11253349
M3 - Conference contribution
AN - SCOPUS:105030342273
T3 - Proceedings of 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things, ICoICI 2025
SP - 1093
EP - 1097
BT - Proceedings of 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things, ICoICI 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Intelligent Cyber Physical Systems and Internet of Things, ICoICI 2025
Y2 - 17 September 2025 through 19 September 2025
ER -