The increasing deployment of complex "black box" AI models in anomaly-based Intrusion Detection Systems (IDS) for future networks has opened up a trust gap that requires human-interpretable explanations in order for analysts to feel confident in acting on alerts. Current approaches to Explainable AI (XAI), such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), do not properly address the challenges inherent in the problem domain. These techniques fundamentally fail from a fidelity standpoint due to their incorrect assumption of independence between features that results in untrustworthy explanations, which are fundamentally based on correlated network data. We address these shortcomings by proposing HiFi-XAI, which leverages a new, novel framework to provide faithful and semantically rich explanations. HiFi-XAI introduces a model-agnostic Conditional Value Attribution Explanation (CVAE), a method based on probabilistic Shapley values that models feature dependencies to ensure explanations are derived from plausible data distributions. These high-fidelity attributions are then translated into actionable, natural-language narratives by a fine-tuned Large Language Model (LLM). We validate our framework through allaware scenario feature ablation studies on the CICIDS2017 and CICIOT2023 datasets. This demonstrates that CVAE consistently identifies more impactful features than SHAP and LIME across five anomaly-based IDS models. Furthermore, we deploy the HiFi-XAI to prove its practical feasibility and test it on a resource-constrained Raspberry Pi 4. Our work presents a complete, end-to-end solution for building trust in AI-driven IDS.

Internet of Things (IoT) connects billions of devices and tiny sensors enabled with Low-Power and Lossy Networks (LLNs) to provide real time data transfer. These LLNs work as s backbone of complete IoT ecosystem which has limited power, memory and processing capability. The routing protocol for such LLNs enabled devices is standardized by IETF in RFC 6550 which is known has Routing Protocol for Low-Power and Lossy Networks (RPL). Due to the constraints of the RPL protocol, it is vulnerable to various new security attacks which needs effective defense solution. Machine Intelligence (including Machine Learning and Deep Learning) plays a great role to deal with detection of recent attacks based on the pattern and behaviour analysis of device presented in the network. This paper introduces a novel hyperparameter-based approach to detect and classify the RPL-based routing attacks. The proposed approach uses a Hyperband tuner search, that finds the optimal hyperparameter such as learning rate and the number of neurons for deep learning model to improve the detection performance. Experiments have been conducted on the ROUT-4-2023 dataset that contains the attack sample of Flooding, Blackhole, DODAG Version number and Rank attack. The results are evaluated against various performance metrics on dataset balance and imbalance scenario which provide the promising findings for attack classification.

The Low-Power and Lossy Network (LLN) is the most important building block in the Internet of Things (IoT), comprising numerous tiny sensor nodes connected together. The Routing Protocol for Low-Power and Lossy Networks (RPL) is an IPv6-based protocol developed by the Internet Engineering Task Force (IETF) to facilitate routing for LLN devices. The Destination Advertisement Objects (DAOs) are transmitted from RPL nodes in the network toward the root node to construct downward routes. The malicious node exploits the DAO transmission mechanism to replay the DAO with a fixed time interval in the network in order to launch the DAO Insider attack. The DAO Insider attack causes a large number of DAO, which contributes to network congestion; as a result, data packets are delayed, and network performance is degraded. This paper proposes a defense solution that monitors DAO timestamps between child and parent nodes, flagging suspicious nodes that exceed a threshold within a time interval, blacklisting, and discarding DAOs from identified malicious nodes. Moreover, it limits the number of DAO transmitted by a child node within a specified time interval to mitigate the impact of an attack. The experiments show that the DAO insider attack has a negative impact on network performance (packet delivery ratio, average end-to-end delay, and throughput) at various DAO replay intervals. The proposed defense solution restores optimal network performance with a high detection rate.

In this study, a closed‐form solution is presented for the constrained water‐filling problem (CWFP) where in powers allocated to the user resources maximise the user's capacity under an interference constraint and a total power constraint. Total power constraint in CWFP is to save the energy in wireless network. To solve CWFP, erstwhile algorithms compute powers for all the resources iteratively. Unlike existing algorithms, the proposed method calculates the number of resources that gets positive (or non‐zero) powers using the concepts of traditional water‐filling problem. Later, powers are allocated to the resolved resources (that gets positive powers) alone using the closed‐form solution, which reduces the number of computations. It can be discerned that the computational complexity of the given solution is of the order of , where is the total number of resources; which is remarkably lower than that of the prior algorithms specified by an order of .

Cognitive radio network (CRN) is one of the prominent technology for the next generation wireless networks. Due to the CR version, the users were classified into two types which are the primary users (PUs) and secondary users (SUs) which are also named as licensed and unlicensed users. The main objective of CRN is to access the underutilized licensed bands of PUs by SUs without any interference to the PUs transmission. In the CR technology, medium access control (MAC) plays a vital role to increase the spectrum efficiency and also minimize the collisions among SUs. So to design an efficient MAC is one of the significant challenges in the CRN. The existed MAC protocols are unable to identify the most appropriate spectrum to access. Thus, spectrum aware token based MAC protocol is proposed to resolve the spectrum selection issue in MAC design for CRN. In this paper, we consider expected spectrum stability time (ESST) as a metric to assign ranks to the available licensed spectrum bands. Simulation results for various parameters show that SAMAR protocol can approximately improve throughput 8% decrease transmission delay 75% compared with IEEE 802.11n. The remaining metric results have demonstrated the performance of existed MAC protocols like IEEE802.11n and TMAC with the proposed MAC.

In a Wireless Sensor Network (WSN) hundreds of tiny sensors with limited resources are accommodated to sense the information from the field. Transfer of gathered information from the sensing field to the base station must be done in proficiently to sustain the network longer. Clustering of sensor nodes is one way to achieve this goal. This paper introduces an Energy Efficient clustered routing protocol based on LEACH-C for WSN. In LEACH-C (Low Energy Adaptive Clustering Hierarchy-Centralized), the cluster heads are selected by the base station randomly. This paper introduces a novel cluster based routing protocol in which, the base station finds the highest energy node among the cluster and mark it as a cluster head for the current time. Thus in the proposed system the energy consumption of various nodes becomes more uniform as compared to LEACH-C. The simulation results indicate that our proposed method leads to efficient transmission of data packets with less energy and therefore increases the network longevity as compared to LEACH-C and LEACH.