Emails stand as a predominant mode of online communication, facilitating the exchange of information. With the ubiquity of emails, there has been a marked rise in unsolicited messages, particularly phishing emails. These deceptive emails aim to mislead recipients, often masquerading as trustworthy entities, to extract confidential information. Embedded with dubious offers, advertisements, malicious links, malware, and trojans, perpetrators deploy these emails with malicious intent, primarily to commit fraud. Consequently, distinguishing between phishing attempts and genuine emails becomes paramount. This study constructs machine learning-based models to detect phishing emails, ensuring accurate discernment between genuine and fraudulent messages. Leveraging two datasets, the Fraud Email Dataset and the Phishing Email Dataset, we developed and evaluated classifiers, including Logistic Regression, Decision Tree, Random Forest, and SVM. The Random Forest model emerged as the most effective, achieving accuracies of 98.72% on the Fraud Email Dataset and 99.15% on the Phishing Email Dataset, demonstrating strong generalizability across diverse phishing patterns. These results underscore the efficacy of ensemble methods for enhancing cybersecurity by reliably detecting phishing emails.

Safe real-world navigation for autonomous vehicles (AVs) requires robust perception and decision-making, especially in complex, multi-agent scenarios. Existing AV datasets are limited by their inability to capture diverse V2X communication scenarios, lack of synchronized multi-sensor data, and insufficient coverage of critical edge cases in multi-vehicle interactions. This paper introduces VRDeepSafety, a novel and scalable VR simulation platform that overcomes these limitations by integrating Vehicle-to-Everything (V2X) communication, including realistic latency, packet loss, and signal prioritization, to enhance AV accident prediction and mitigation. VRDeepSafety generates comprehensive datasets featuring synchronized multi-vehicle interactions, coordinated V2X scenarios, and diverse sensor data, including visual, LiDAR, radar, and V2X streams. Evaluated with our novel deep-learning model, VRFormer, which uniquely fuses VR sensor data with V2X using a probabilistic Bayesian inference, as well as a hierarchical Kalman and particle filter structure, VRDeepSafety achieved an 85% accident prediction accuracy (APA) at a 2 s horizon, a 17% increase in 3D object detection precision (mAP), and a 0.3 s reduction in response time, outperforming a single-vehicle baseline. Furthermore, V2X integration increased APA by 15%. Extending the prediction horizon to 3–4 s reduced APA to 70%, highlighting the trade-off between prediction time and accuracy. The VRDeepSafety high-fidelity simulation and integrated V2X provide a valuable and rigorous tool for developing safer and more responsive AVs.

Over the past few years, phishing has evolved into an increasingly prevalent form of cybercrime, as more people use the Internet and its applications. Phishing is a type of social engineering that targets users' sensitive or personal information. This paper seeks to achieve two main objectives: first, to identify the most effective classifier for detecting phishing among 40 classifiers representing six learning strategies. Secondly, it aims to determine which feature selection method performs best on websites with phishing datasets. By analyzing three unique datasets on phishing and evaluating eight metrics, this study found that Random Forest and Random Tree were superior at identifying phishing websites compared with other approaches. Similarly, GainRatioAttributeEval, along with InfoGainAttributeEval, performed better than the five alternative feature selection methods considered in this study.

Due to the low carbon emissions, minimal maintenance requirements, and the cost effective of operation, plug in electric vehicles (PEVs) are getting more and more popular in today's automotive industry. However, to satisfy the increasing growing number of PEVs on the roads, their charging demand effects these key parts relating to the distribution network: power loss, voltage stability and harmonic distortion. Furthermore, a major issue is posed by the demanding PEV peak charging power on the grid at public charging stations (CSs). Furthermore, the optimized installation location of CSs has an important impact in shaping both the behavior of EV users and the investment decision for CSs. Hence, this paper proposes a new approach to determine the best locations of CSs inside cities. Our proposed scheme takes into account the travel time of PEVs towards CSs considering the horizontal displacement between PEVs and CSs. Moreover, for our proposed scheme, the influence of traffic for both; conventional vehicles and PEVs will be taken into account. Our placement problem will be formulated as a Mixed Integer non-linear Programming (MINLP), and a hybrid heuristic solution is utilized to solve the problem using the Ant Lion Optimizer and Genetic Algorithm (GA) technique. A realistic performance assessment performed in metropolitan setting reveals the robustness of the proposed CS placement approach when considering different charging metrics. Based on the results of the base scenario compared to the scenario A, scenario B, and scenario C, the travel time has been improved by approximately $5.614 \%, 1.9924 \%$, and $\mathbf{9. 3 1 3 \%}$, respectively, resulting in a more efficient and quicker journey.

Hydrogen vehicles are facing significant challenges, including safety risks in the event of leakage, high costs associated with physical testing, and fuel cell inefficiency under dynamic conditions; to address these concerns, we propose VR-H2Safe, a cyber-physical platform that combines high-fidelity simulation, physics-informed reinforcement learning (RL), and secure vehicle-to-everything (V2X) communication. Using ANSYS Fluent Large Eddy Simulation (LES) to train real-time predictive models, the platform’s digital twin simulates hydrogen leakage with 92% spatio-temporal correlation compared to high-fidelity LES-CFD benchmarks at key monitoring points. Furthermore, we introduce the H2-LEAK protocol, which extends the SAE J2735 standard with a 128-bit risk vector and blockchain authentication, which provides hazard warnings in less than 2 s with 95% spoofing resistance. In addition, our physics-informed AI system optimizes the fuel cell performance, achieving a 10% increase in energy efficiency and a 58% reduction in thermal violations during hardware verification. The experimental findings of urban, tunnel, and road conditions prove that VR-H2Safe accelerates the process of safety verification and reduces the engineering validation phase from 14 to 10 weeks.