Machine Learning Based Anomaly Detection for Network Intrusion Detection in Cyber Security

DOI

10.2991/978-94-6463-787-8_42How to use a DOI?

Keywords

Anomaly detection; Random Forest; Logistic Regression; cyber security; machine learning; network traffic; performance metrics; cyber threats

Abstract

In the pursuit of improved cybersecurity, this study assesses the effectiveness of two prominent techniques for machine learning, including Logistic Regression and Random Forest Classifier—in the area of anomaly identification in network data. Strong detection systems are more important than ever as businesses struggle with more complex cyberattacks. Using a wide range of standards, like precision, recall, accuracy, and ROC-AUC scores, this research provides a complete assessment of the models’ performance. Results reveal that both algorithms achieve commendable accuracy levels; however, they struggle significantly with anomaly identification, exposing crucial vulnerabilities in their application. The Random Forest Classifier effectively captures normal traffic patterns yet encounters challenges with false positives and detecting anomalies. Conversely, Logistic Regression excels in classifying normal instances but fails to recognize any anomalies, highlighting a significant shortcoming. By elucidating these complexities, the research underscores the urgent need for advancements in machine learning methodologies for cybersecurity. The present investigation not only pinpoints crucial deficiencies in existing methodologies but also establishes a basis for subsequent investigations focused on creating increasingly intricate and flexible anomaly detection systems, ultimately reinforcing safeguards against the ever-changing terrain of cyber hazards.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ravi Kumar Burman
AU  - Abhishek Kumar
AU  - Sunaina Kumari
AU  - Nishant Kumar
AU  - Binod Kumar
AU  - Vikas Kumar
PY  - 2025
DA  - 2025/07/17
TI  - Machine Learning Based Anomaly Detection for Network Intrusion Detection in Cyber Security
BT  - Proceedings of the Recent Advances in Artificial Intelligence for Sustainable Development (RAISD 2025)
PB  - Atlantis Press
SP  - 532
EP  - 546
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-787-8_42
DO  - 10.2991/978-94-6463-787-8_42
ID  - Burman2025
ER  -