ABSTRACT Deep learning‐based intrusion detection systems have high accuracy and low false alarm rates. However, there are challenges to deploy deep learning models in the vulnerable, resource‐constrained Internet of Things. Therefore, two deep learning models are proposed: Lightweight Intrusion Detection System using Feedforward Neural Network (LIDSuFNN) and Lightweight Intrusion Detection System using Convolutional Neural Network (LIDSuCNN). In the models, the feedforward neural network is compressed using neuron pruning and the convolutional neural network is compressed using filter pruning. Then, quantization has been applied to the models. The models are trained and tested on standard datasets and synthetic datasets. A generative artificial intelligence model, Conditional Tabular Generative Adversarial Network (CTGAN), has been used to generate synthetic data. The models have been compared with the baselines and results are analyzed. Experimental results show that the proposed models require less training time and memory than the baselines, with approximately similar performance. The reduction of various parameters is due to the fact that pruning and quantization have removed unnecessary calculations from the networks. Statistical analysis has also been done to show the superiority of the proposed techniques.

ABSTRACT The healthcare industry is undergoing a transformative shift with the integration of blockchain technology and Artificial Intelligence (AI). Traditional healthcare systems struggle with data security, lack of transparency, and inefficiencies in resource allocation, leading to increased risks and operational challenges. AI‐driven models provide intelligent solutions by enabling predictive diagnostics, fraud detection, and personalised treatment plans, while blockchain ensures data integrity, security, and decentralised access control. The synergy between AI and blockchain enhances decision‐making, optimises resource utilisation and fosters trust in healthcare systems by automating processes with greater transparency and security. AI‐powered analytics can extract meaningful insights from vast healthcare datasets, improving patient outcomes and streamlining supply chains. Meanwhile, blockchain's immutable ledger safeguards medical data, preventing breaches and ensuring regulatory compliance. This paper presents a comprehensive review of blockchain solutions in healthcare, exploring their impact on enhancing security, promoting transparency and improving energy efficiency. Additionally, this paper also presents insights on the integration of AI and blockchain in healthcare. It categorises existing blockchain‐based frameworks and highlights emerging trends, challenges, and future research directions. This review aims to serve as a foundational reference for researchers and practitioners developing secure, transparent, and intelligent healthcare systems.

In real-world networks, such as social networks, the occurrence of random failures or external attacks on network components can lead to the discontinuation of information flow in the network. Hence, ensuring the existence and robustness of these networks is a crucial concern these days. To address this problem, one possible solution is to redesign the connection between individual nodes in the network using some budget-constrained rewiring operations. Multiple rewiring operations help in building trust between individuals and strengthening their connections, further enhancing overall connectivity and information flow in the network. The effectiveness of rewiring approaches is determined by analyzing some important facts, such as the rewiring cost, adherence to budget constraints, and enhancement in network connectivity. To assess the efficacy of rewiring approaches, the rewiring cost has been regularly updated after each rewiring operation by measuring the evolution of the size of the giant component in the social network. The performance of the proposed budget-constrained rewiring approaches is evaluated against the random rewiring approach. The results show the superiority of the proposed approaches on the benchmark real-world dataset. By leveraging these budget-constrained rewiring approaches, it becomes possible to design social systems that exhibit enhanced stability and reliability of social networks in the face of various disruptions.

The rapid development of Big Data technology supports the advancement of many fields like industrial automation, smart healthcare, distributed systems, and many more. Big data is large and heterogeneous data generated from different sources, such as Internet of Things (IoT) devices, weather forecasting, traffic management systems, etc. However, in a distributed smart healthcare industry, unauthorized users or devices can illegally access healthcare Big Data, as well as control the sensor or IoT-enabled devices connected to a patient's body. They can even alter patients' healthcare Big Data by inserting false and misleading data, which may even cause death to the patient. This study presents a lightweight privacy-preserving user authentication scheme to solve the above-said problems in a distributed smart healthcare system. The proposed scheme prevents unauthorized users from getting access to the healthcare system by establishing a secure session for the authorized user. Here, the password protection mechanism allows only a legitimate user to access and modify the patient's healthcare Big Data. The security strength and effectiveness of the proposed authentication scheme is evaluated in this article, which show that it is more efficient and secure than the state-of-the-art schemes.

Nowadays, the relevance of women-only educational institutes is questionable due to various reasons that include social uplifting, ample opportunities, and a free mindset among the population. Though women colleges and universities bring many female students to the purview of the traditional education system every year, other activities like research works and collaborative projects are still a concern for the educationists. In the current manuscript, the role of leading women-only universities and institutions is analyzed throughout India, to scrutinize its impact and opportunities in the research domain. All types of educational institutions and collaborative research work among them are represented as a social network. Different centrality metrics, such as closeness, betweenness, and eigenvector, are utilized to examine the influence of the individual institutes in the collaborative research network. An overlapping community detection method is proposed to perceive the posture of gender-biased universities in the mixed institutional model. The supremacy of the proposed approach is presented over the real-life benchmark datasets. The analytical results exhibit notable improvement over the state-of-the-art approaches and unfold a contemporary framework for strategic analysis in the higher education sector.

Federated Learning (FL) enabled the reliability and robustness of 5G communication networks for wireless edge computing to provide collaborative Deep Learning (DL) of complex models while protecting privacy for healthcare systems. Wireless end devices are more susceptible to corruption due to the vulnerability offered by open network settings, however, this creates security issues and lessens the effectiveness of DL-based security models for healthcare systems. Furthermore, disaster reliability in communication networks has garnered unprecedented attention from governments and companies, particularly during the current COVID-19 pandemic scenario. In this work, a novel reliable personalized Federated Learning-based Customized Inequality-Aware Federated Learning (CusIAFL) technique is proposed for securing color images while communicating with a wireless network. The proposed technique adjusts each data sampling to the local target during optimization using knowledge of client-label availability. The work that is being presented uses a hybrid technique to maintain consistency in the time-series data. and a novel Pix2Pix Generative Adversarial Network (GAN) technique is used to generate realistic images. This novel work is tested on different non-medical and medical images. The experimental results have been evaluated using performance metrics, namely accuracy, entropy, PSNR, HD95, SSIM, and MSE. Furthermore, the accuracy varies from 89 to 93 percent with different datasets outperforming well with existing SOTA techniques. The outcomes demonstrate that the proposed CusIAFL-based scheme is more effective than the State-Of-The-Art (SOTA) models.

No abstract available.

Cloud storage system provides on-demand and pay-per-use storage models with low computing costs. However, this storage system suffers from various security risks. Blockchain technology is an advanced technique that stores data in a distributed manner, and once the data are stored, it cannot be altered. Therefore, a blockchain-based distributed architecture has been proposed in this paper for the cloud storage system. The proposed scheme utilizes the functionality of the smart contract to provide security features to the stored cloud data. The proposed scheme encodes the data before uploading it to the cloud server to achieve confidentiality. Furthermore, the proposed system includes an enhanced optimization technique and a challenge-response-based integrity checking mechanism, which provides a more secure cloud environment. The proposed technique also minimizes the system bandwidth cost using an enhanced fruit fly optimization algorithm that optimizes the node failure repair process. The experimental results and performance evaluation show that the proposed scheme is secured and reliable for the cloud computing environment.

In the healthcare network, the Internet of Things (IoT) devices are connected to the network for enabling remote monitoring of patients’ health. IoT Device (IoTD) security, however, is a serious concern because typical security measures might not be appropriate for IoTD, making them naturally vulnerable to physical and copying attacks. Therefore, device authentication is a very essential security concern for IoT networks. Additionally, the storage and processing power of these devices are constrained. To address all these requirements, physically unclonable functions (PUFs) for device authentication is a potential strategy. In this article, an advanced lightweight authentication scheme for IoTD is proposed by using PUF. This scheme provides robust authentication without storing any sensitive information on the device’s memory and establishes the session key exchange process simultaneously. Moreover, this scheme preserves device privacy by including a temporary identity, which is updated at the end of each session. The effectiveness of this novel model is assessed, and results demonstrate that it is more effective and secure than many existing schemes.

Scene text detection is complicated and one of the most challenging tasks due to different environmental restrictions, such as illuminations, lighting conditions, tiny and curved texts, and many more. Most of the works on scene text detection have overlooked the primary goal of increasing model accuracy and efficiency, resulting in heavy-weight models that require more processing resources. A novel lightweight model has been developed in this article to improve the accuracy and efficiency of scene text detection. The proposed model relies on ResNet50 and MobileNetV2 as backbones with quantization used to make the resulting model lightweight. During quantization, the precision has been changed from float32 to float16 and int8 for making the model lightweight. In terms of inference time and Floating-Point Operations Per Second, the proposed method outperforms the state-of-the-art techniques by around 30–100 times. Here, well-known datasets, i.e., ICDAR2015 and ICDAR2019, have been utilized for training and testing to validate the performance of the proposed model. Finally, the findings and discussion indicate that the proposed model is more efficient than the existing schemes.

The exponential growth of the Internet of Things (IoT) technologies requires high data security. Here, data security is very critical as all IoT devices transfer data over the Internet. The fine-grained access control provided by the ciphertext policy attribute-based encryption (CP-ABE) technique can be considered as a potential solution to this issue. However, most of the CP-ABE schemes use bilinear pairing operations for its internal working, which is expensive for any resource constraint device. An elliptic curve cryptography (ECC) based CP-ABE scheme can be well suited for resource constraint IoT framework because ECC takes less computational time. This article proposes a novel CP-ABE technique based on ECC to achieve fine-grained access control over data or resources. The proposed technique includes multiple attribute authorities to manage attributes and key generation, which can reduce the work overhead of having a single authority in traditional CP-ABE systems. In addition, the proposed scheme outsources the decryption process to a user assistant entity to reduce the decryption overhead of the end-users. To prove the efficiency of the proposed scheme, both formal security analysis and performance comparisons are presented in this article. The result and findings prove the effectiveness of the proposed scheme over some well-known schemes.

The cab-sharing system provides a platform for drivers and riders with shared trip services, providing significant benefits, such as decreasing traffic congestion, reducing travel costs, and limicting energy consumption, which improve the business of transportation. However, existing cab-sharing systems mainly depend on the centralized authority to provide many services, increasing privacy concerns and facing the single point of failure issue. Also, these systems expose drivers’ or riders’ locations and personal information that increase security issues, and charge high fees for services due to the involvement of third-party providers. Therefore, this paper proposes a decentralized and secure cab-sharing system to provide ride-sharing services using blockchain technology without any trusted third party. The proposed system uses the blockchain structure to preserve the driver’s or rider’s information, such as personal details, travel price, pickup or drop-off locations, departure or arrival date, and time. Furthermore, it implements the reputation feature to rate drivers and riders based on their travel history or behaviors without any centralized authority that allows users to select them based on their past experiences on the system. The proposed architecture is deployed using the Ethereum platform and functionality is designed using smart contracts. The performance evaluation and experimental results show that the proposed system requires low computational overheads and provides an efficient cab-sharing platform.

Blockchain technology provides a secure and reliable platform for managing data in various application areas, such as supply chain management, multimedia, financial sector, food sector,Internet of Things (IoT), healthcare, and many more. The recent emergence of blockchain with IoT provides significant growth in the healthcare industry to improve security, privacy, efficiency, and transparency with more business opportunities. Nevertheless, conventional healthcare schemes suffer from various security attacks like collusion, phishing, masquerade, etc. Therefore, a privacy-preservingDistributed Application (DA)is proposed in this paper using blockchain technology to create and maintain healthcare certificates. Here, the distributed application provides an interface between the blockchain network and system objects like healthcare centers, verifiers, and regular authorities to generate and issue medical documents. In addition, it also ensures security by specifying rules using various smart contracts. To evaluate the performance of the proposed scheme, various experimental tests are conducted using the Etherscan tool for measuring operation cost, latency, and processing time. Here, the efficiency of the proposed system is also compared to the existing systems in terms of latency, throughput, and response time. The experimental results and comparative analysis show that the proposed work is more efficient than the existing techniques.

Abstract Nowadays, blockchain and Internet of Things (IoT) are two emerging areas of the Information Technology (IT) sector. These two emerging areas are used in various fields, such as supply chain, logistics and automotive industry. Due to the low processing power and storage space of IoT devices, users' medical information is usually saved in a centralized third party like a clinical repository or a cloud computing environment. Thus, in many cases, users lose control of their medical information, which can result in security disclosure and a single‐point impediment. So, an advanced solution is required to improve the data sharing process, while restricting it in terms of security. Blockchain technology with IoT can significantly affect the healthcare industry by improving its efficiency, security and transparency, as well as can provide more business opportunities. The efficient sharing of Electronic Health Record (EHR) can improve the treatment process, diagnosis accuracy, security and privacy. This article proposes a blockchain‐based IoT architecture to provide enhanced security of healthcare data by using Identity‐Based Encryption (IBE) algorithm. Here, the smart contract defines all the basic operations of the healthcare system, which can be beneficial to all stakeholders. Many experiments are executed to evaluate the efficiency of the proposed scheme. The results show that the proposed scheme is better than the existing renowned schemes.

In a cloud environment, traditional approaches are used to encrypt any data by using 0 and 1 that increase data security issues because of the presence of numerous malicious users and hackers over the internet. Deoxyribonucleic Acid (DNA) computing can be one of the best solutions to improve data security in which data are encrypted using the DNA bases: Thymine (T), Guanine (G), Cytosine (C) and Adenine (A). Along with data security, access control is another major issue of a cloud environment as the searching time of the owner of any data, the system overheard and the accessing time of a file or data are high during data access. A novel DNA computing based secure and fast Access Control Model (ACM) is proposed in this article to solve all these major problems. In the proposed scheme, the Cloud Service Provider (CSP) keeps a table or list for fast data accessing. Here, a 1024-bit DNA computing based random key is generated by using the user's secret information, and the same key is utilized for data encryption. Theoretical analysis along with many experimental results prove the efficiency and effectiveness of the proposed access control model over some well-known existing models.

Community detection algorithms (CDAs) are aiming to group nodes based on their connections and play an essential role in the complex system analysis. However, for privacy reasons, we may want to prevent communities or a group of nodes in the complex industrial network from being discovered in some instances, leading to the topics on community deception. In this paper, we introduce and formalize two intelligent community deception methods to conceal the nodes from various CDAs. We used node-based matrices, persistence and safeness scores, to formalize the optimization problems to confound the CDAs. The persistence score is used to destabilize the constant communities in the network while the safeness score is used to assess the level of hiding of a node from CDAs. The objective functions aim to minimize the persistence score and maximize the safeness score of the nodes in the network. From the simulation results, it can be analyzed that the proposed strategies are intelligently concealing the community information in the complex industrial system.

Today, the size of a multimedia file is increasing day by day from gigabytes to terabytes or even petabytes, mainly because of the evolution of a large amount of real-time data. As most of the multimedia files are transmitted through the internet, hackers and attackers try to access the users’ personal and confidential data without any authorization. Thus, maintaining a strong security technique has become a significant concerned to protect the personal information. Deoxyribonucleic Acid (DNA) computing is an advanced field for improving security, which is based on the biological concept of DNA. A novel DNA-based encryption scheme is proposed in this article for protecting multimedia files in the cloud computing environment. Here, a 1024-bit secret key is generated based on DNA computing and the user's attributes and password to encrypt any multimedia file. To generate the secret key, the decimal encoding rule, American Standard Code for Information Interchange value, DNA reference key, and complementary rule are used, which enable the system to protect the multimedia file against many security attacks. Experimental results, as well as theoretical analyses, show the efficiency of the proposed scheme over some well-known existing schemes.

Summary With the rapid development of the Internet, resource and knowledge sharing are two major problems experienced due to the presence of many hackers and malicious users. In this paper, an efficient and secure access control model has been proposed for the cloud computing environment for resource and knowledge sharing by using attribute‐based encryption (ABE), distributed hash table (DHT) network, and identity‐based timed‐release encryption (IDTRE). Here, at first, data or resources are encrypted by using the attributes of users, and encrypted data are divided into the encapsulated ciphertext and extracted ciphertext. Then, IDTRE algorithm has been used to encrypt the decryption key and combined the ciphertext of the key with the extracted ciphertext for creating the ciphertext shares. At last, the ciphertext shares are distributed into the DHT network, and encapsulated ciphertext are stored on the cloud servers. Both the performance and security analysis show the proficiency of the proposed scheme over the existing schemes in a cloud environment.

Summary Cloud computing is an emerging computing area that allows on‐demand, scalable, flexible, and low‐cost services to the users. In cloud computing, access control and security are two major problems. In this paper, a novel authentication scheme using Chebyshev chaotic maps has been presented. The proposed model satisfies many security factors, such as scalability of login, mutual authentication, freedom of password change, two‐factor security, and forward security. Two‐factor security is a method that requires two credentials for authentication, where the first factor may be something that users know and the second factor may be something that users have. Forward security assures the confidentiality of the user's session key, even if the private key of the server is compromised. In addition, the proposed scheme provides users with untraceability and anonymity, which means that any kind of adversary neither gets the identities of users or servers nor link several sessions with a user or server. The proposed model is secured under the computational Diffie–Hellman assumption of Chebyshev polynomials in the random oracle model. Moreover, security and performance analysis show that the proposed scheme can resist different security attacks in cloud computing environment and it is better than existing schemes. Copyright © 2016 John Wiley & Sons, Ltd.

Cloud computing is a very trending technology because of its efficiency, cost effectiveness, pay‐per‐use, flexibility and scalability. Data security and access control are two significant issues experienced while availing these advantages of cloud computing. Access control can be defined as a procedure by which a user can access data or file or any kind of resources from a server. A new data access control model has been proposed in this paper for efficient data accessing, which can minimise many problems, such as high searching time for providing the public key of the data owner, high data accessing time, maintenance of the database, etc. The proposed scheme is evaluated in terms of both theoretical and experimental results, which show the proficiency of the proposed scheme over the existing schemes in a cloud computing environment.