Ibrahim S. Alsukayti

In the dynamic and ever-evolving realm of network security, the ability to accurately identify and classify portscan attacks both inside and outside networks is of paramount importance. This study delves into the underexplored potential of fusing graph theory with machine learning models to elevate their anomaly detection capabilities in the context of industrial Internet of things (IIoT) network data analysis. We employed a comprehensive experimental approach, encompassing data preprocessing, visualization, feature analysis, and machine learning model comparison, to assess the efficacy of graph theory representation in improving classification accuracy. More specifically, we converted network traffic data into a graph-based representation, where nodes represent devices and edges represent communication instances. We then incorporated these graph features into our machine learning models. Our findings reveal that incorporating graph theory into the analysis of network data results in a modest-yet-meaningful improvement in the performance of the tested machine learning models, including logistic regression, support vector machines, and K-means clustering. These results underscore the significance of graph theory representation in bolstering the discriminative capabilities of machine learning algorithms when applied to network data.

The exponential growth of the Internet of Things (IoT) is being witnessed nowadays in different sectors. This makes IoT data communications more complex and harder to manage. Addressing such a challenge using a centralized model is an ineffective approach and would result in security and privacy difficulties. Technologies such as blockchain provide a potential solution to enable secure and effective management of IoT data communication in a distributed and trustless manner. In this paper, a novel lightweight blockchain-centric IoT architecture is proposed to address effective IoT data communication management. It is based on an event-driven smart contract that enables manageable and trustless IoT data exchange using a simple publish/subscribe model. To maintain system complexity and overhead at a minimum, the design of the proposed system relies on a single smart contract. All the system operations that enable effective IoT data communication among the different parties of the system are defined in the smart contract. There is no direct blockchain–IoT-device interaction, making the system more useable in wide IoT deployments incorporating IoT devices with limited computing and energy resources. A practical Ethereum-based implementation of the system was developed with the ability to simulate different IoT setups. The evaluation results demonstrated the feasibility and effectiveness of the proposed architecture. Considering varying-scale and varying-density experimental setups, reliable and secure data communications were achieved with little latency and resource consumption.