Automated Teller Machine (ATM) is a major tool for electronic banking (e-Banking). It enables the availability of banking services anytime and anywhere. Presently, most ATMs communicate only with the banking system networks for security monitoring and enforcements. This paper presents a customer-aware surveillance system for all attempted ATM banking activities. Employing a graphical modeling tool (Unified Modeling Language), the design integrates an additional input, through an inbuilt IP Camera that stealthily captures the ATM user facial image, which is automatically transmitted to the mobile device of the bank account owner, through some dedicated artificial intelligent agents, for remote certification, which either authorizes the transaction appropriately or signals a security-violation alert to the banking security system. Thus, online and real-time monitoring of ATM banking transactions is enabled, reporting suspected unusual attempts to account owner and bank security unit. Hence, customer-level visibility of ATM banking security, through remote certification of a proxy ATM user, is made possible.
Phishing email attacks pose a serious and persistent cybersecurity threat, which require robust detection mechanisms. Current approaches often suffer from setbacks some of which are outdated and imbalanced datasets. This paper introduces the PCA-based Enhanced Phishing Email Attack Detection (EPEAD) framework, which is a novel method for highly accurate phishing email identification. The EPEAD framework generates a custom balanced dataset of 50,000 phishing and benign emails, integrating modern techniques. A detailed pre-processing module extracts relevant features, including email content, URL characteristics and sender authenticity. Principal Component Analysis (PCA) is applied for dimensionality reduction. Supervised machine learning algorithms (Logistic Regression, Random Forest, k-Nearest Neighbors, Decision Tree, Naïve-Bayes, Artificial Neural Networks) are then trained and evaluated using standard metrics. The EPEAD framework achieved an outstanding highest accuracy of 98.38% in phishing email identification, which outperforms many models reliant on public datasets, even with traditional algorithms. This high accuracy highlights the critical role of superior data and meticulous feature engineering. The custom-generated, balanced and feature-rich dataset, combined with PCA, offers a transparent and reliable defence against evolving threats, including LLM-rephrased emails.