Open Access

ARTICLE

Advanced BERT and CNN-Based Computational Model for Phishing Detection in Enterprise Systems

Brij B. Gupta^1,2,3,4,*, Akshat Gaurav⁵, Varsha Arya^6,7, Razaz Waheeb Attar⁸, Shavi Bansal⁹, Ahmed Alhomoud¹⁰, Kwok Tai Chui¹¹

1 Department of Computer Science and Information Engineering, Asia University, Taichung, 413, Taiwan
2 Symbiosis Centre for Information Technology (SCIT), Symbiosis International University, Pune, 411057, India
3 Center for Interdisciplinary Research, University of Petroleum and Energy Studies (UPES), Dehradun, 248007, India
4 University Centre for Research and Development (UCRD), Chandigarh University, Chandigarh, 140413, India
5 Computer Engineering, Ronin Institute, Montclair, NJ 07043, USA
6 Department of Business Administration, Asia University, Taichung, 413, Taiwan
7 Department of Electrical and Computer Engineering, Lebanese American University, Beirut, 1102, Lebanon
8 College of Business Administration, Management Department, Princess Nourah bint Abdulrahman University, Riyadh, 11671, Saudi Arabia
9 Department of Research and Innovation, Insights2Techinfo, Jaipur, 302001, India
10 Department of Computer Sciences, Faculty of Computing and Information Technology, Northern Border University, Rafha, 91911, Saudi Arabia
11 Department of Electronic Engineering and Computer Science, Hong Kong Metropolitan University (HKMU), Hong Kong, 518031, China

* Corresponding Author: Brij B. Gupta. Email:

Computer Modeling in Engineering & Sciences 2024, 141(3), 2165-2183. https://doi.org/10.32604/cmes.2024.056473

Received 23 July 2024; Accepted 26 September 2024; Issue published 31 October 2024

Abstract

Phishing attacks present a serious threat to enterprise systems, requiring advanced detection techniques to protect sensitive data. This study introduces a phishing email detection framework that combines Bidirectional Encoder Representations from Transformers (BERT) for feature extraction and CNN for classification, specifically designed for enterprise information systems. BERT’s linguistic capabilities are used to extract key features from email content, which are then processed by a convolutional neural network (CNN) model optimized for phishing detection. Achieving an accuracy of 97.5%, our proposed model demonstrates strong proficiency in identifying phishing emails. This approach represents a significant advancement in applying deep learning to cybersecurity, setting a new benchmark for email security by effectively addressing the increasing complexity of phishing attacks.

---

Keywords

---