Interactive and Explainable Optimized Learning for DDoS Detection in Consumer IoT Networks
Makhduma F. Saiyed, Irfan Al‐Anbagi, M. Shamim Hossain
Abstract
The integration of Internet of Things (IoT) in consumer environments enhances convenience and security while increasing Human-Computer Interaction (HCI). However, this increased interactivity has also increased the vulnerability of Consumer IoT (CIoT) networks to cyber threats, mainly Distributed Denial of Service (DDoS) attacks. The DDoS attacks, which vary in volume, present substantial challenges to these networks’ operational integrity and customer trust. This paper introduces the Artificial Intelligence (AI)-driven (ADEPT) system that utilizes explainable and optimized deep-ensemble learning with pruning for DDoS detection. The system uses attention-based ensemble DL for DDoS detection, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. To address the resource constraints of edge devices in CIoT networks, the system uses Differential Evolution (DE)-based pruning and quantization techniques, optimizing the model for efficient deployment on edge nodes while preserving high performance. An HCI interface is designed to allow network administrators and researchers to engage with the system through dynamic visualizations, facilitating complex data interpretation and empowering administrators to refine detection strategies. The interface, integrating SHapley Additive exPlanations (SHAP) and risk assessment, enhances model transparency and interpretability, highlighting the synergy of HCI and AI. The ADEPT system is evaluated using an experimental testbed and CIoT datasets and has demonstrated over 90% accuracy in detecting high- and low-volume DDoS attacks.