A Novel Attention-Based CNN for Robust DDoS Attack Detection in IoT Smart Homes

Smart homes, increasingly reliant on interconnected Internet of Things (IoT) devices, face escalating security risks, particularly from Distributed Denial of Service (DDoS) attacks. Current DDoS detection methods often falter against the complexity and variability of modern attack traffic. This research proposes a novel solution: an attention-enhanced Convolutional Neural Network (CNN) for superior DDoS detection in IoT smart home environments. Our approach integrates an attention mechanism to dynamically focus the CNN on the most critical features within network traffic data, improving both accuracy and efficiency. Rigorous testing using the comprehensive CICIoT 2023 dataset validates the effectiveness of our model. The results demonstrate substantial improvements in accuracy, precision, recall, and F1-score compared to traditional CNN-based methods. This enhanced approach significantly bolsters the resilience of IoT smart home networks against DDoS attacks, offering a critical advancement in securing this rapidly expanding sector. The superior performance highlights the efficacy of attention mechanisms in handling the dynamic nature of DDoS attacks within the complex IoT ecosystem.