In modern industrial environments, the security and sustainability of Industrial Control Systems (ICS) have become crucial. This comprehensive review examines the transformative potential of Artificial Intelligence (AI) in ICS, focusing on technologies like Machine Learning (ML), Deep Learning (DL), Large Language Models (LLMs), and cloud computing. Moreover, this research explores integrating existing and proposed sustainable practices within the ICS framework, with a particular emphasis on energy efficiency and carbon footprint reduction, to enhance the overall sustainability of ICS. This review employed a systematic approach to select relevant articles from multiple reputable databases, such as Scopus, IEEE Explore, Science Direct, ACM digital library, Web of Science, and IET digital library, including 250 articles that provide valuable insights into the intersection of AI, security, and sustainability in ICS. This review examines vulnerabilities in ICS, such as data breaches, insider threats, and malware, emphasizing the need for effective anomaly detection. It highlights how AI technologies like anomaly detection and predictive analytics can enhance threat detection and response in ICS by improving accuracy and efficiency. The review offers insights to researchers and professionals on the future of secure, sustainable ICS, supporting a resilient industrial landscape that meets cybersecurity, compliance, and sustainability goals.

In the modern era of digital technology, the rapid distribution of news via social media platforms substantially contributes to the propagation of false information, presenting challenges in upholding the accuracy and reliability of information. This study presents an updated approach that utilizes graph neural networks (GNNs) alongside with advanced deep learning techniques to improve the identification of false information. In contrast to traditional approaches that primarily rely on analyzing text and assessing the credibility of sources, our methodology utilizes the structural information of news propagation networks. This allows for a detailed comprehension of the interconnections and patterns that are indicative of misinformation. By analyzing the intricate, graph-based connections between news items, our approach not only overcomes the constraints of conventional fake news detection methods but also demonstrates significant enhancements in detection accuracy. This paper emphasizes the revolutionary nature of utilizing GNNs in the field of fake news detection. It also examines the potential consequences of our research in reducing the propagation of false information. Our model achieved an impressive accuracy rate of 97%, demonstrating a significant improvement in its ability to identify and classify fake news.The findings highlight the substantial improvement in the ability to detect fake news provided by GNNs in comparison to traditional methods, demonstrating promising growth in the struggle against false information.

Link prediction is a key problem in the field of undirected graph, and it can be used in a variety of contexts, including information retrieval and market analysis. By “undirected graphs”, we mean undirected complex networks in this study. The ability to predict new links in complex networks has a significant impact on society. Many complex systems can be modelled using networks. For example, links represent relationships (such as friendships, etc.) in social networks, whereas nodes represent users. Embedding methods, which produce the feature vector of each node in a graph and identify unknown links, are one of the newest approaches to link prediction. The Deep Walk algorithm is a common graph embedding approach that uses pure random walking to capture network structure. In this paper, we propose an efficient model for link prediction based on a hill climbing algorithm. It is used as a cost function. The lower the cost is, the higher the accuracy for link prediction between the source and destination node will be. Unlike other algorithms that predict links based on a single feature, it takes advantage of multiple features. The proposed method has been tested over nine publicly available datasets, and its performance has been evaluated by comparing it to other frequently used indexes. Our model outperforms all of these measures, as indicated by its higher prediction accuracy.

KGs are often incomplete, missing entities and relations, an issue addressed by Knowledge Graph Completion (KGC) methods that predict missing elements. Mean Reciprocal Rank (MRR), Mean Rank (MR), and Hit@k (e.g., MRR) are commonly used to assess the performance of KGC models. A major challenge in evaluating KGC models however, lies in comparing their performance across multiple datasets and metrics. A model may outperform others on one dataset but underperform on another, making it difficult to determine overall superiority. Moreover, even within a single dataset, different metrics such as MRR and Hit@1 can yield conflicting rankings, where one model excels in MRR while another performs better in Hit@1, further complicating model selection for downstream tasks. To address this fragmentation, we propose KG-EDAS, Inspired by Inspired by Multi-Criteria Decision-Making (MCDM), Evaluation based on Distance from Average Solution (EDAS), a robust meta-metric that synthesizes model performance across multiple datasets and diverse evaluation criteria into a single normalized score ($M_{i} \in[0, 1]$). Experiments on five standard datasets show that KG-EDAS produces stable, interpretable rankings highly correlated with MRR ($\rho=0.93$) while resolving conflicts across metrics. In addition, it integrates multi-metric, multidataset performance into a unified ranking, offering a consistent, robust, and generalizable framework that resolves conflicting rankings and supports informed model selection in real-world KGC applications. We argue that KG-EDAS offers a principled foundation for standardized evaluation in KGC-enabling fair comparisons and supporting automated model selection.