Message Queue Telemetry Transport (MQTT), a widely used messaging protocol in IoT applications, faces significant security challenges, particularly with denial-of-service attacks and ensuring continuous, secure communication. Traditional security measures, like TLS/SSL, often introduce CPU overhead, bandwidth issues, and require complex certificate management. This paper has two main objectives: first, to provide a comprehensive review of MQTT security, detailing how MQTT operates, the associated security vulnerabilities, and existing solutions; and second, to propose a framework called the Stateful Authentication Framework (SAF). SAF enhances MQTT security through two key components: the SAF authentication protocol and a Large Language Model (LLM)-based Intrusion Detection System (IDS). The SAF protocol uses client-state information to establish secure, stateful interactions between clients and brokers, and incorporates a multi-factor authentication mechanism to prevent replay attacks and unauthorized access. Our evaluation of SAF shows that it significantly improves MQTT security, with Scyther simulations confirming the robustness of the protocol against known generic attacks. Additionally, the LLM-based IDS that integrates SAF’s security policies provides an advanced approach for detecting intrusions. To our knowledge, this is the first integrated approach combining a state-based authentication protocol and LLM-based IDS to tackle MQTT security challenges.

Abstract Generally, the existing Intrusion Detection Systems (IDS) solutions suffer from low detection accuracy for some attack types compared with the overall detection accuracy of attacks. The data imbalance technically affects the ratio of detection accuracy of low frequent attacks class (e.g. zero‐day attack) compared to attacks with more instances. Therefore, IDS‐based machine learning algorithms potentially suffer from high false‐positive rates. To overcome the limitation of existing solutions, a hyper‐clustering model is proposed for dynamic intrusion detection based on the Density‐Based Spatial Clustering of Applications with Noise (DBSCAN) and cosine similarity. The proposed solution develops the standard DBSCAN by adding a new evolving process based on distance measures between the clusters to overcome the imbalance dataset. Moreover, a new classifier is proposed based on cosine similarity to predict the labelling of abnormal behaviour. The experimental results show that the proposed model outperformed the original DBCAN and the related works. The mean silhouette of the proposed DBSCAN achieves a high score of 0.87 compared to other solutions. Furthermore, the proposed DBSCAN reduces the mean square error from 0.66 to 0.13 and achieves 86.82%, 79.10% and 90.03% in general accuracy on KDDTest+, KDDTest‐21 NSL‐KDD and UNSW‐NB15 benchmark datasets, respectively.

In this era, digital technologies such as artificial intelligence, the Internet of Things (IoT) and blockchain are gaining popularity in research and academia. The supply chain management application is the key to achieving many benefits from AIoT and blockchain technology. However, these technologies have many issues, such as sustainability, a green environment, and multiconstraints (e.g., time, energy, cost, and CO2) for supply chain management applications. This article presents sustainable, secure blockchain-assisted AIoT and green multiconstraint supply chain systems. Initially, we present a secure and sustainable methodology that securely validates the supply chain management system data. For the green environment, we consider the problem a combinatorial problem consisting of different constraints such as time, energy, cost, and carbon dioxide (CO2). To solve this problem for supply chain management jobs, we present a multiconstraint genetic algorithm deep convolutional neural network (MCGA-DCNN) algorithm methodology. The objective is to reduce total processing time, total processing energy consumption, cost, and the CO2 environment as a green environment for supply chain management jobs. The genetic algorithm is evolutionary, where the fitness function optimizes the multiconstraint weights at the runtime based on DCNN and provides the optimal solutions for jobs. Simulation results show that MCGA-DCNN minimized the time, energy, cost, and CO2 and securely validated all transactions for all supply chain management jobs compared to existing schemes.

COVID-19 is the disease evoked by a new breed of coronavirus called the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Recently, COVID-19 has become a pandemic by infecting more than 152 million people in over 216 countries and territories. The exponential increase in the number of infections has rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) and machine learning (ML), which can assist the healthcare sector in providing quick and precise COVID-19 diagnosis. Therefore, this paper provides a comprehensive review of the most recent DL and ML techniques for COVID-19 diagnosis. The studies are published from December 2019 until April 2021. In general, this paper includes more than 200 studies that have been carefully selected from several publishers, such as IEEE, Springer and Elsevier. We classify the research tracks into two categories: DL and ML and present COVID-19 public datasets established and extracted from different countries. The measures used to evaluate diagnosis methods are comparatively analysed and proper discussion is provided. In conclusion, for COVID-19 diagnosing and outbreak prediction, SVM is the most widely used machine learning mechanism, and CNN is the most widely used deep learning mechanism. Accuracy, sensitivity, and specificity are the most widely used measurements in previous studies. Finally, this review paper will guide the research community on the upcoming development of machine learning for COVID-19 and inspire their works for future development. This review paper will guide the research community on the upcoming development of ML and DL for COVID-19 and inspire their works for future development.

Since the past decades, the world has been transformed into a digital society, where every individual is living with a unique identifier. The primary purpose of this id is to distinguish from others and to deal with digital machines which are surrounding the world. Recently, many researchers showed that the brain electrical activity or electroencephalogram (EEG) signals could provide robust and unique features that can be considered as a new biometric authentication technique, given that accurately methods to decompose the signals must also be considered. This paper proposes a novel method for EEG signal denoising based on the multi-objective Flower Pollination Algorithm and the Wavelet Transform (MOFPA-WT) to extract useful features from denoised signals. MOFPA-WT is tested using a standard EEG signal dataset, namely, EEG motor movement/imagery dataset, and its performance is evaluated using three criteria: (i) accuracy, (ii) true acceptance rate, and (iii) false acceptance rate. We show that the proposed method can achieve results that are comparable to the state-of-the-art ones, as well as we draw future directions towards the research area.