Newsfeeds
Most recent issue published online in the International Journal of Critical Computer-Based Systems.
International Journal of Critical Computer-Based Systems
-
An enhanced internet of medical things using blockchain-enabled elliptic curve cryptography for security and privacy
As internet of medical things (IoMT) devices proliferate, the need for robust security measures becomes paramount to protect sensitive health information from cyber threats and unauthorized access. Therefore, this paper proposes a blockchain-enabled with elliptic curve cryptography (ECC) to bolster security and privacy in medical data transmission. The proposed framework leverages the decentralized nature of blockchain, ensuring data integrity and transparency while utilizing ECC for efficient encryption and decryption processes. This combination not only addresses the scalability and performance issues associated with traditional cryptographic methods but also facilitates secure data sharing among healthcare stakeholders. Through a series of experiments and comparative analyses, the effectiveness of the proposed system is evaluated, demonstrating significant improvements in security resilience and operational efficiency. The findings highlight the potential of blockchain-enabled ECC as a transformative solution for securing IoMT ecosystems, ultimately contributing to safer and more reliable healthcare services.
-
A deterministic approach with Markov chain algorithm to impose higher order security in dynamic wireless sensor networks
Wireless sensor networks are deployed based on their application environment. Since WSN are modality based, they sense data based on the type of data, they must sense. Unless otherwise we deploy proper algorithms and governance on to the sensor nodes, they behave in a normal way. We tried an attempt to provide a pilot scheme to establish a scheme called 'ORDER- optimal retrospective decision enrichment for reliability', which analyses the previous tasks of the sensor nodes and categorise those nodes under different categories related to specific tasks. The algorithm ORDER analyses the tasks and assigns the tasks to the sensor nodes and monitor whether the tasks are being performed in a time bound manner without any compromise into security aspects. Our model is compared with the existing benchmarked approaches and found better in terms of reliability, data integrity and data consistency, throughput and BER.
-
Intrusion detection and optimal path-based energy efficient data transmission using MLVQ and BM-MSOA in MANET
In the wireless network, the MANET is a core technology that offers multi-hop communications between the source node (SN) and destination node (DN). The MANETs are susceptible to diverse security attacks due to the broadcast behaviour of transmission, restricted computation ability, and increasing application areas. Thus, intrusion detection is needed to handle these security issues. Thus, this work develops an efficient intrusion detection system (IDS) in MANET utilising MLVQ neural network (NN). The proposed system offers energy-efficient data transmission (DT) by sending data via the optimal path. Then, the MLVQ NN detects the attacked data and normal data in the intrusion detection phase. The data are isolated and stored in a log file. Later, the optimal path is chosen by BM-MSOA centred on the MN residual energy and path distance. The proposed methodology detects the intrusion with higher accuracy and minimal energy consumption (EC) compared with the prevailing techniques.
-
Collaborative AI-based malware detection through reliable clustered federated learning
Artificial intelligence (AI) has become integral to enhancing decision-making and personalising experiences across various domains. However, data privacy remains a major challenge when training machine learning models. This study proposes a novel framework combining an innovative aggregation technique and lightweight differential privacy (DP) to secure communications in federated learning (FL). The framework supports AI-based malware detection using eight clients organised into three clustering configurations. Performance is evaluated using five classifiers: random forest (RFC), decision tree (DTree), extreme gradient boosting (XGB), support vector classifier (SVC), and multi-layer perceptron (MLP). The XGB classifier achieved the highest accuracy, up to 99.6%. Results show that the framework maintains high accuracy while preserving data privacy, offering a promising solution for secure AI deployment in sensitive sectors such as finance, healthcare, and cybersecurity.