A Simulation Framework for AI-Driven, Software Defined Network-Powered, Self-Healing 5G Security with Slice Isolation

DOI

10.2991/978-94-6239-713-2_33How to use a DOI?

Keywords

5G Network Slicing; Software Defined Networking; DDoS Detection; Machine Learning Security; Network Simulation; Ryu Controller; Random Forest Classification; Self-Healing Networks; Real-time Mitigation

Abstract

With the emergence of 5G networks, network slicing provides a virtualized network on shared infrastructure, increasing the attack surface to various threats, including DDoS attacks. Traditional security systems cannot handle the dynamic characteristics of 5G networks and therefore require a smart, automated solution. This paper introduces a simulation framework called Sentinel AI that combines Mininet, Ryu-based SDN control, and an optimized Random Forest classifier to enable real-time DDoS detection and automated self-healing mitigation in 5G networks using network slicing, without human intervention. The proposed system achieved 98.4% accuracy, 96.9% precision, 97.8% recall, a 0.7% false positive rate, and a 0.991 AUC-ROC for real-time DDoS detection across 6 test cases. Additionally, it achieved a 1.5-second average response time, more than 99.5% reduction in attack traffic, and 0% verified impact on other slices for automated mitigation across 6 different test cases. The proposed system operates at 60-70% CPU and 2.6 GB of RAM, even under high-attack conditions involving multiple slices, making it suitable for 5G network security research.

Copyright

© 2026 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  - Ajit Pillai
AU  - Akshita Shetty
AU  - Chaitravi Reddy
AU  - Ritisa Behera
AU  - Sanjay Vidhani
PY  - 2026
DA  - 2026/06/25
TI  - A Simulation Framework for AI-Driven, Software Defined Network-Powered, Self-Healing 5G Security with Slice Isolation
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 432
EP  - 452
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_33
DO  - 10.2991/978-94-6239-713-2_33
ID  - Pillai2026
ER  -