The rise in intrusions on network and IoT systems has led to the development of artificial intelligence (AI) methodologies in intrusion detection systems (IDSs). However, traditional AI or machine learning (ML) methods can compromise accuracy due to the vast, diverse, and dynamic nature of the data generated. Moreover, many of these methods lack transparency, making it challenging for security professionals to make predictions. To address these challenges, this paper presents a novel IDS architecture that uses deep learning (DL)-based methodology along with eXplainable AI (XAI) techniques to create explainable models in network intrusion detection systems, empowering security analysts to use these models effectively. DL models are needed to train enormous amounts of data and produce promising results. Three different DL models, i.e., customized 1-D convolutional neural networks (1-D CNNs), deep neural networks (DNNs), and pre-trained model TabNet, are proposed. The experiments are performed on seven different datasets of TON_IOT. The CNN model for the network dataset achieves an impressive accuracy of 99.24%. Meanwhile, for the six different IoT datasets, in most of the datasets, the CNN and DNN achieve 100% accuracy, further validating the effectiveness of the proposed models. In all the datasets, the least-performing model is TabNet. Implementing the proposed method in real time requires an explanation of the predictions generated. Thus, the XAI methods are implemented to understand the essential features responsible for predicting the particular class.

In this paper, we address the thermal rise and Quality-of-Service (QoS) provisioning issue for an intra-body Wireless Body Area Network (WBAN) having in-vivo sensor nodes. We propose a thermal-aware QoS routing protocol, called TLQoS, that facilitates the system in achieving desired QoS in terms of delay and reliability for diverse traffic types, as well as avoids the formation of highly heated nodes known as hotspot(s), and keeps the temperature rise along the network to an acceptable level. TLQoS exploits modular architecture wherein different modules perform integrated operations in providing multiple QoS service with lower temperature rise. To address the challenges of highly dynamic wireless environment inside the human body. TLQoS implements potential-based localized routing that requires only local neighborhood information. TLQoS avoids routing loop formation as well as reduces the number of hop traversal exploiting hybrid potential, and tuning a configurable parameter. We perform extensive simulations of TLQoS, and the results show that TLQoS has significant performance improvements over state-of-the-art approaches.

The emergence of heterogeneous applications with diverse requirements forresource-constrained Wireless Body Area Networks (WBANs) poses significant challengesfor provisioning Quality of Service (QoS) with multi-constraints (delay and reliability) while preserving energy efficiency. To address such challenges, this paper proposes McMAC,a MAC protocol with multi-constrained QoS provisioning for diverse traffic classes in WBANs. McMAC classifies traffic based on their multi-constrained QoS demands andintroduces a novel superframe structure based on the "transmit-whenever-appropriate" principle, which allows diverse periods for diverse traffic classes according to their respective QoS requirements. Furthermore, a novel emergency packet handling mechanism is proposedto ensure packet delivery with the least possible delay and the highest reliability. McMAC is also modeled analytically, and extensive simulations were performed to evaluate itsperformance. The results reveal that McMAC achieves the desired delay and reliability guarantee according to the requirements of a particular traffic class while achieving energy efficiency.

Due to domain variability and developing attack tactics, intrusion detection in heterogeneous and dynamic IoT systems is still a crucial challenge. For cross-domain intrusion detection, this paper proposes a novel algorithm, X-FuseRLSTM, a dual-path feature fusion framework that is attention guided and coupled with a residual LSTM architecture. The proposed algorithm is the combination of four major steps: first, feature extraction using deep encoder and sparse transformer; second, feature fusion of the extracted features and reducing the fused features; third, the classification model; and last, explainable artificial intelligence (XAI). The classification model used is a deep neural network and residual long short-term memory (RLSTM). The model effectively incorporates both spatial and temporal correlations in network traffic data, which improves its detection capability. The model predictions are explained using the XAI techniques. Extensive experiments on datasets including TON_IoT Network, NSL-KDD, and CICIoMT 2024 with both 19-class and 6-class variations show that X-FuseRLSTM achieves the highest accuracy of 99.40% on network, 99.72% on NSL-KDD, and 97.66% for 19-class and 98.05% for 6-class on CICIoMT 2024 datasets. The suggested method is appropriate for practical IoT security applications since it provides strong domain generalization and explainability while preserving computational efficiency.