The Internet of Things (IoT) is currently seeing tremendous growth due to new technologies and big data. Research in the field of IoT security is an emerging topic. IoT networks are becoming more vulnerable to new assaults as a result of the growth in devices and the production of massive data. In order to recognize the attacks, an intrusion detection system is required. In this work, we suggested a Deep Learning (DL) model for intrusion detection to categorize various attacks in the dataset. We used a filter-based approach to pick out the most important aspects and limit the number of features, and we built two different deep-learning models for intrusion detection. For model training and testing, we used two publicly accessible datasets, NSL-KDD and UNSW-NB 15. First, we applied the dataset on the Deep neural network (DNN) model and then the same dataset on Convolution Neural Network (CNN) model. For both datasets, the DL model had a better accuracy rate. Because DL models are opaque and challenging to comprehend, we applied the idea of explainable Artificial Intelligence (AI) to provide a model explanation. To increase confidence in the DNN model, we applied the explainable AI (XAI) Local Interpretable Model-agnostic Explanations (LIME ) method, and for better understanding, we also applied Shapley Additive Explanations (SHAP).

Internet of Things (IoT) applications are growing in popularity for being widely used in many real-world services. In an IoT ecosystem, many devices are connected with each other via internet, making IoT networks more vulnerable to various types of cyber attacks, thus a major concern in its deployment is network security and user privacy. To protect IoT networks against various attacks, an efficient and practical Intrusion Detection System (IDS) could be an effective solution. In this paper, a novel anomaly-based IDS system for IoT networks is proposed using Deep Learning technique. Particularly, a filter-based feature selection Deep Neural Network (DNN) model where highly correlated features are dropped has been presented. Further, the model is tuned with various parameters and hyper parameters. The UNSW-NB15 dataset comprising of four attack classes is utilized for this purpose. The proposed model achieved an accuracy of 84%. Generative Adversarial Networks (GANs) were used to generate synthetic data of minority attacks to resolve class imbalance issues in the dataset and achieved 91% accuracy with balanced class dataset.