@inproceedings{9665698e488a41898579105d8d5bb4d6,
title = "Optimized Lightweight VGG-Based AI Model for Phishing Detection in Cloud Applications",
abstract = "Phishing is a persistent threat in cybersecurity, often targeting users in cloud-hosted environments. In this context, we proposed an optimized lightweight VGG-based AI model for efficient phishing detection. The model enhances the traditional VGG16 architecture by reducing complexity and integrating a KNN-based classifier, ensuring scalability and suitability for cloud deployment. Feature selection using the ANOVA F-test reduces the dataset and improves the computational efficiency. The model outperforms traditional machine learning classifiers, achieving a precision, recall, and F1-score of 93.3\%. These results demonstrate the effectiveness of the proposed solution in mitigating phishing threats in cloud-based applications.",
keywords = "ANOVA F-test, Cloud Computing, Phishing Detection, VGG",
author = "Akshat Gaurav and Varsha Arya and Chui, \{Kwok Tai\} and Gupta, \{Brij B.\}",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE Conference on Dependable and Secure Computing, DSC 2025 ; Conference date: 18-10-2025 Through 20-10-2025",
year = "2025",
doi = "10.1109/DSC65356.2025.11260894",
language = "English",
series = "2025 IEEE Conference on Dependable and Secure Computing, DSC 2025",
booktitle = "2025 IEEE Conference on Dependable and Secure Computing, DSC 2025",
}