Risk-aware Selective Quarantine Mechanism for Enterprise WiFi Networks based on Machine Learning Detection

Read full text Summarise with VIRAT
Authors: Heribertus Widi Wismono, Vera Suryani
Cited by: 0
References: 43

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Enterprise WiFi networks face escalating exposure to Advanced Persistent Threats (APT) whose stealthy, multi-stage behaviour often bypasses traditional detection systems and triggers overly disruptive quarantine responses.This study introduces a unified framework that integrates machine-learning-based identification, contextual risk modelling, and selective quarantine into an Susceptible-Infected-Identification-Quarantine-Recovered (SIIQR) inspired containment architecture to deliver adaptive and operationally aware defence.Using the SCVIC-APT-2021 dataset, the proposed mechanism achieves highly accurate threat detection highly accurate threat detection with F1 scores above 0.99 for gradient boosting based models, while reducing unnecessary full isolation from 98% under conventional quarantine to 9% under the proposed risk aware quarantine.Despite this substantial reduction in isolation severity, infection containment remains consistently high with an infection reduction ratio above 0.99 across repeated runs, and service continuity improves by up to 8%.Experimental results demonstrate that this approach transforms quarantine from a rigid binary action into a precise control strategy capable of mitigating sophisticated attacks without destabilizing network operations.The findings confirm that risk aware selective quarantine provides a robust and practical solution for automated enterprise WiFi security.

Fields of Study & Subjects

Network Security and Intrusion Detection Adversarial Robustness in Machine Learning Network Packet Processing and Optimization

Publication details

Journal / source
International journal of intelligent engineering and systems
Volume
19
Issue
4
Pages
314–333
Publication date
23 March 2026
Language
EN