Enhancing IoT Network Security through Adaptive Curriculum Learning and XAI

2025-01-20

AI Summary

To address the challenges of model lightweighting, interpretability, and dynamic adaptability in IoT network security, this paper proposes an adaptive curriculum learning framework tailored for edge deployment. The method introduces a stage-wise curriculum-driven lightweight neural architecture integrating feature distillation, quantization-aware pruning, and LIME-based interpretability analysis. Additionally, it constructs a hybrid ensemble model combining random forests, XGBoost, and staged learning to enhance generalization and noise robustness. Evaluated on the CIC-IoV-2024, CIC-APT-IIoT-2024, and EDGE-IIoT datasets, the framework achieves attack detection accuracies of 98%, 98%, and 97%, respectively. It demonstrates high accuracy, strong robustness against adversarial perturbations and noisy inputs, and efficient execution under stringent edge-device resource constraints—enabling real-time, interpretable, and adaptive intrusion detection in heterogeneous IoT environments.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Adversarial Attacks & Robustness
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

To address the critical need for secure IoT networks, this study presents a scalable and lightweight curriculum learning framework enhanced with Explainable AI (XAI) techniques, including LIME, to ensure transparency and adaptability. The proposed model employs novel neural network architecture utilized at every stage of Curriculum Learning to efficiently capture and focus on both short- and long-term temporal dependencies, improve learning stability, and enhance accuracy while remaining lightweight and robust against noise in sequential IoT data. Robustness is achieved through staged learning, where the model iteratively refines itself by removing low-relevance features and optimizing performance. The workflow includes edge-optimized quantization and pruning to ensure portability that could easily be deployed in the edge-IoT devices. An ensemble model incorporating Random Forest, XGBoost, and the staged learning base further enhances generalization. Experimental results demonstrate 98% accuracy on CIC-IoV-2024 and CIC-APT-IIoT-2024 datasets and 97% on EDGE-IIoT, establishing this framework as a robust, transparent, and high-performance solution for IoT network security.

Problem

• Internet of Things
• network security
• IoT security

Innovation

• Adaptive Learning System
• Interpretable Artificial Intelligence
• IoT Security Enhancement