Enhanced intrusion detection system IoT network security model by feed forward neural network and machine learning

The security of IoT networks has become a significant concern owing to the increasing count of cyber threats. Traditional Intrusion Detection Systems (IDS) struggle to detect sophisticated attacks in real-time due to resource constraints and evolving attack patterns. This study proposes a novel IDS that integrates deep learning (DL) and machine learning (ML) approaches to improve IoT security. The main objective is to develop a hybrid IDS combining Feed Forward Neural Networks (FFNN) and XGBoost to improve attack detection accuracy while minimizing computational overhead. The proposed methodology involves data preprocessing, feature selection utilizing Principal Component Analysis (PCA), and classification employing FFNN and XGBoost. The model is trained and evaluated on the CIC IoT 2023 dataset, which comprises real-time attack data, ensuring its practical relevance. The proposed model is estimated on the CIC IoT 2023 dataset, demonstrating superior accuracy (99%) compared to existing IDS techniques. This study provides valuable insights into improving IDS models for IoT security, addressing challenges such as dataset imbalance, feature selection, and classification accuracy. Results demonstrate that the hybrid FFNN-XGBoost model outperforms standalone FFNN and XGBoost classifiers, achieving an accuracy of 99%. Compared to existing IDS models, the proposed approach significantly enhances precision, recall, and F1-score, ensuring robust intrusion detection. This research contributes to IoT security by introducing a scalable and efficient hybrid IDS model. The findings offer a strong basis for future advancements in intrusion detection using DL and ML approaches.