Enhancing IoT Security: A Novel Feature Engineering Approach for ML-Based Intrusion Detection Systems
Afsaneh Mahanipour, Hana Khamfroush
TL;DR
The paper addresses security challenges in IoT by targeting edge-based intrusion detection with a novel feature-engineering pipeline. It combines Binary Quantum-inspired Artificial Bee Colony (BQABC) feature selection with Genetic Programming (GP) feature construction to create informative, high-level features and a reduced feature subset for efficient ML-based IDS. Evaluations on NSL-KDD, UNSW-NB15, and BoT-IoT show improved accuracy and lower false positives, while reducing computational cost compared to several metaheuristic baselines. The approach demonstrates a practical edge-oriented solution with strong statistical support (Wilcoxon tests) and highlights potential extensions to distributed IoT settings and more constructed features. Overall, the method offers a compelling trade-off between detection performance and resource usage for real-time IoT security at the edge.
Abstract
The integration of Internet of Things (IoT) applications in our daily lives has led to a surge in data traffic, posing significant security challenges. IoT applications using cloud and edge computing are at higher risk of cyberattacks because of the expanded attack surface from distributed edge and cloud services, the vulnerability of IoT devices, and challenges in managing security across interconnected systems leading to oversights. This led to the rise of ML-based solutions for intrusion detection systems (IDSs), which have proven effective in enhancing network security and defending against diverse threats. However, ML-based IDS in IoT systems encounters challenges, particularly from noisy, redundant, and irrelevant features in varied IoT datasets, potentially impacting its performance. Therefore, reducing such features becomes crucial to enhance system performance and minimize computational costs. This paper focuses on improving the effectiveness of ML-based IDS at the edge level by introducing a novel method to find a balanced trade-off between cost and accuracy through the creation of informative features in a two-tier edge-user IoT environment. A hybrid Binary Quantum-inspired Artificial Bee Colony and Genetic Programming algorithm is utilized for this purpose. Three IoT intrusion detection datasets, namely NSL-KDD, UNSW-NB15, and BoT-IoT, are used for the evaluation of the proposed approach.