The exponential expansion of the Internet of Things (IoT) has fundamentally transformed the way people, machines, and gadgets communicate, resulting in unparalleled levels of interconnectedness. Nevertheless, the growth of IoT has also brought up notable security obstacles, requiring the creation of strong intrusion detection systems to safeguard IoT networks against hostile actions. This study investigates the utilization of fog computing architectures in conjunction with machine learning approaches to improve the security of the IoT. The UNSW-NB15 dataset, containing an extensive range of network traffic characteristics, is used as the basis for training and assessing the machine learning models. The study specifically applies and evaluates the performance of various models, including linear regression, Ridge classifier, SGD classifier, and ensemble learning. Furthermore, the findings indicate that these models are capable of accurately identifying intrusions, with success rates of 94%, 97%, 96.60%, and 96.50%, respectively. The Ridge Classifier demonstrates exceptional accuracy, highlighting its potential for effective implementation in IoT security frameworks. The results emphasize the efficacy of combining machine learning with fog computing to tackle the distinct security obstacles faced by IoT networks. In the future, our work will prioritize optimizing these models for real-time applications, improving their scalability, and investigating more advanced ensemble strategies to enhance detection accuracy. The project intends to enhance these areas to create a comprehensive and scalable intrusion detection system that can offer strong security solutions for the growing IoT environment. This will guarantee the integrity and dependability of linked devices and systems.

The swift integration of intelligent technologies at higher institutions of learning has greatly improved efficiency of operations, learning conditions, and administration. But the evolution of cybersecurity issues presented by the integration of Internet of Things (IoT) devices, cloud-based systems, and interconnected systems has complicated and shifted the complexity of these issues, which old and standard methods of periodic auditing cannot effectively tackle. The present paper suggests an AI-based Cyber Risk Auditing Framework (AI-CRAF) of continuous and real-time risk assessment in smart educational campuses. The framework combines sophisticated machine learning and deep learning models to identify the threats, anomalies, and dynamic risk assessment with references to vulnerabilities to the system and their potential impact. The suggested model is tested on a big data set of 1,247,334 events within 12 months that contains various attack cases and regular operations. The experimental values indicate a high detection accuracy of 96.2 %, a true detection rate of 94.8 %, a low false positive rate of 2.1 % and an AUC-ROC value of 0.978. Also, the framework shortens 97.1 the time spent on an average incident response by 41.9 minutes to 1.2 minutes as compared to conventional methods.

The rapid expansion of renewable energy systems has contributed to the extensive use of cloud-based monitoring applications that receive and process massive amounts of operational telemetry information. Nevertheless, the dynamic and complex nature of renewable energy systems makes it difficult to detect abnormal behaviors that can adversely impact the reliability and efficiency of energy generation. This paper proposes an artificial intelligence-based anomaly detection system designed for cloud-controlled renewable energy systems. The proposed solution integrates deep representation learning models with a contextual drift-based anomaly scoring mechanism to identify anomalous operation patterns in multivariate renewable energy telemetry data. Normal system behavior is learned using an autoencoder-based architecture, and the proposed Context-Aware Residual Drift Scoring (CARDS) algorithm enhances anomaly detection by identifying contextual anomalies in system performance. Experimental evaluation was conducted on multivariate renewable energy telemetry data under cross-validation setups consistent with those used for comparison models. The proposed framework achieved a detection accuracy of 97.4% and an ROC–AUC score of 0.98, outperforming baseline algorithms such as Isolation Forest, LSTM-based detection, and Transformer-based models. These findings demonstrate that the suggested AI-based system offers a viable and scalable approach to enhancing reliability and operational intelligence in cloud-based renewable energy monitoring systems.

Man-in-the-Browser (MitB) attacks represent a sophisticated class of web-based threats that manipulate browser functionality to intercept and modify user transactions in real-time. Traditional server-side detection mechanisms often fail to identify these attacks due to their client-side nature and encrypted communication channels. This paper presents a novel client-side runtime integrity agent that employs forensic monitoring and machine learning-based anomaly detection to identify MitB attacks at their source. The proposed system integrates DOM integrity verification, memory forensic analysis, and behavioral pattern recognition to detect malicious browser modifications before they can compromise user sessions. Our experimental evaluation demonstrates a detection accuracy of 97.3% with a false positive rate of 2.1%, significantly outperforming existing client-side detection methods. The system successfully identified various MitB attack vectors, including Zeus, SpyEye, and custom injection payloads, while maintaining a minimal computational overhead of less than 3% CPU utilization.