Hershey, Pennsylvania
New York, New YorkBeijing, China
Integrating AI and Semantic Web Technologies for Robust Phishing Detection in Virtual Realities

Integrating AI and Semantic Web Technologies for Robust Phishing Detection in Virtual Realities

Liang Zhou (Jiading District Central Hospital, Shanghai University of Medicine and Health Sciences, Shanghai, China), Akshat Gaurav (Ronin Institute, USA), Wadee Alhalabi Alhalabi (Department of Computer Science, Immersive Virtual Reality Research Group, King Abdulaziz University, Jeddah, Saudi Arabia), Varsha Arya (Hong Kong Metropolitan University, Hong Kong & Center for Interdisciplinary Research, University of Petroleum and Energy Studies (UPES), Dehradun, India), and Eaman Alharbi (Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia)
Copyright: © 2025 |Pages: 19
DOI: 10.4018/IJSWIS.371415
Article PDF Download
Open access articles are freely available for download

Abstract

Phishing detection is a critical challenge in virtual realities, where malicious activities can compromise user security. This paper presents a novel approach integrating AI and Semantic Web Technologies for robust phishing detection. The proposed model preprocesses text data and leverages a reduced six-layer BERT encoder to extract contextual embeddings. Outputs from BERT, including classifier, attention, and encoder layers, are combined with features derived from Semantic Web Technologies and a custom deep learning layer to form a unified representation. The concatenated features are passed to a linear layer for classification. Experiments demonstrate superior performance, achieving 95\% accuracy, 96\% F1-score, and a 0.99 ROC-AUC, outperforming standard machine learning models. This framework provides a reliable phishing detection solution for virtual environments.
Article Preview
Top

Paper Organization

The paper is organized as follows. The related work section reviews existing phishing detection methods and highlights gaps in current approaches and the motivation for a hybrid framework. The proposed methodology section describes the detailed architecture, including preprocessing, the reduced six-layer BERT encoder, semantic web technologies integration, deep learning layers, and the classification process, as supported by mathematical formulations. The results and discussion present the model’s performance using metrics such as accuracy, F1-score, and receiver operating characteristic (ROC)-AUC alongside a comparative analysis with standard machine learning models. Finally, the conclusion summarizes the findings.

Complete Article List

Search this Journal:
Reset
Volume 21: 1 Issue (2025)
Volume 20: 1 Issue (2024)
Volume 19: 1 Issue (2023)
Volume 18: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 17: 4 Issues (2021)
Volume 16: 4 Issues (2020)
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing