Every aspect of the 21st century has undergone a revolution because of the Internet of Things (IoT) and smart computing technologies. These technologies are applied in many different ways, from monitoring the state of crops and the moisture level of the soil in real-time to using drones to help with chores such as spraying pesticides. The extensive integration of both recent IT and conventional agriculture has brought in the phase of agriculture 4.0, often known as smart agriculture. Agriculture intelligence and automation are addressed by smart agriculture. However, with the advancement of agriculture brought about by recent digital technology, information security challenges cannot be overlooked. The article begins by providing an overview of the development of agriculture 4.0 with pros and cons. This study focused on layered architectural design, identified security issues, and presented security demands and upcoming prospects. In addition to that, we propose a security architectural framework for agriculture 4.0 that combines blockchain technology, fog computing, and software-defined networking. The suggested framework combines Ethereum blockchain and software-defined networking technologies on an open-source IoT platform. It is then tested with three different cases under a DDoS attack. The results of the performance analysis show that overall, the proposed security framework has performed well.

Nowadays, there is a growing need for Internet of Things (IoT)-based mobile healthcare applications that help to predict diseases. In recent years, several people have been diagnosed with diabetes, and according to World Health Organization (WHO), diabetes affects 346 million individuals worldwide. Therefore, we propose a noninvasive self-care system based on the IoT and machine learning (ML) that analyses blood sugar and other key indicators to predict diabetes early. The main purpose of this work is to develop enhanced diabetes management applications which help in patient monitoring and technology-assisted decision-making. The proposed hybrid ensemble ML model predicts diabetes mellitus by combining both bagging and boosting methods. An online IoT-based application and offline questionnaire with 15 questions about health, family history, and lifestyle were used to recruit a total of 10221 people for the study. For both datasets, the experimental findings suggest that our proposed model outperforms state-of-the-art techniques.

The research area of Vehicular Ad-Hoc Network (VANET) is rapidly expanding for different reasons. The main factors responsible for this are the unstable topology, fast vehicle movement, and security vulnerabilities. Identifying malicious attacks in vehicular ad-hoc networks is necessary to enhance the security and reliability of communication between all vehicles in the system. The intruders carry out numerous malicious attacks. The focus of this paper is to identify and mitigate attacks like Botnet, Sybil, DoS, Wormhole, PortScan, Blackhole, and BruteForce. The present work proposes an Improved LeeNET (I-LeeNet) architecture to identify and mitigate unidentified attack types. The suggested architecture intelligently blends Convolutional Neural Networks (CNN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) to provide real-time solutions to unidentified attacks. The proposed approach includes a module KIDS for known attack detection and another module UIDS for learning and identifying previously unidentified attacks. The KIDS module uses ANFIS classification to identify destructive attacks. ANFIS and CNN use the UIDS module to identify unknown attacks on VANET further. The efficacy of the proposed I-LeeNet is tested on three different datasets, such as i-VANET, ToN-IoT, and CIC-IDS 2017. The results section discusses the testing in a regressive manner. In addition, the experimental results are compared to other advanced methods. The average accuracy achieved by the proposed method is 97.21% on i-VANET, 97.75% on ToN-IoT, and 96.66% on the CIC-IDS 2017 dataset. The analysis suggests the proposed method is promising and can be applied in real-time.

The 2019 coronavirus disease (COVID-19) spread quickly throughout the world, causing a global pandemic. After proper diagnosis, digital images storing patient personal health information are saved and transferred over a public network. As a result, the security aspects of preserving sensitive patient health information are becoming crucial. In this study, we presented an encryption system for COVID-19 CT images to address this problem. This work describes an effective inter-intra bit level (BL) pixel processing solution for secret medical images through an encryption technique that does not rely on pixel correlation. The hybrid multi-logistic sine chaotic map (MLSCM) technique combines logistic and sine maps, improving randomness and ergodicity and leading to stronger security. The utilization of hybrid MLSCM technology further enhances the time efficiency. The system’s security is strengthened by the simultaneous rearrangement and spreading of pixels, which helps to prevent statistical and frequent types of attacks. The SHA-512 hash algorithm is incorporated to generate highly secure keys, ensuring resilience against brute force and differential attacks. Row-wise and column-based permutation algorithms further enhance security by disrupting statistical processes. The suggested method yields an optimal entropy of 7.9982, which is more significant than the comparable recorded works. The proposed work beats other existing work on calculating the number of pixel change rates (NPCR) and the unified average change intensity (UACI), with values of 99.6233 and 33.5065, respectively. The avalanche impact for key sensitive analysis has been confirmed with a key space of 1.5491 × 2⁵²⁶, enough to resist multiple attacks.