Adversarial Machine Learning in Intrusion Detection Systems: Threats  and Mitigations

Nitin Bodade

Adversarial Machine Learning in Intrusion Detection Systems: Threats and Mitigations

Authors

Nitin Bodade

Keywords:

Adversarial Machine Learning, Intrusion Detection Systems, Evasion Attacks, Data Poisoning, Adversarial Training, Network Security, Deep Learning Robustness, Generative Adversarial Networks

Abstract

Network Intrusion Detection Systems (IDS) built on machine learning and deeplearning models have become the backbone of modern cyber defense, offering the ability todetect novel and previously unseen attacks that signature-based systems cannot recognize.However, the same statistical learning properties that give these models their detection power also make them susceptible to adversarial machine learning

References

[1] M. H. Bhuyan, D. K. Bhattacharyya, and J. K. Kalita, "Network anomaly detection: Methods, systems and tools," IEEE Communications Surveys & Tutorials, vol. 16, no. 1, pp. 303-336, 2014.

Downloads

Published

2022-11-15

How to Cite

Nitin Bodade. (2022). Adversarial Machine Learning in Intrusion Detection Systems: Threats and Mitigations . Journal of Computational Analysis and Applications (JoCAAA), 30(2), 1250–1261. Retrieved from https://www.eudoxuspress.com/index.php/pub/article/view/5762