Enhancing Phishing Detection in Semantic Web Systems Using Optimized Deep Learning Models
Phishing detection in Semantic Web systems is crucial to safeguarding users from malicious attacks. In this context, this work presents a deep learning-based phishing attack detection model using MobileBERT for feature extraction and hyperparameter optimization using covariance matrix adaptation evolution strategy (CMA-ES). The model obtained a 95% classification accuracy. Important benchmarks like accuracy, recall, and F1-score show good ability to discriminate between phishing and legitimate emails. Applying CMA-ES, which improved detection accuracy, helps to verify the model even more. MobileBERT and CMA-ES together offer Semantic Web systems a fresh, efficient method of phishing detection.
Authors
- Razaz Waheeb Attar (ORCID: https://orcid.org/0000-0001-9819-7945)
- Akshat Gaurav (ORCID: https://orcid.org/0000-0002-5796-9424)
- Varsha Arya (ORCID: https://orcid.org/0000-0001-7549-4429)
- Shavi Bansal
- Liang Zhou (ORCID: https://orcid.org/0000-0002-5957-2674)
- Ahmed Alhomoud (ORCID: https://orcid.org/0000-0003-2782-3106)
Institutions
- Princess Nourah bint Abdulrahman University (SA)
- Northern Border University (SA)
- Jiading District Central Hospital (CN)
- Shanghai University of Medicine and Health Sciences (CN)
- Ronin Institute (US)
- University of Business and Technology (SA)
- Lebanese American University (LB)
- University of Petroleum and Energy Studies (IN)
Publication Details
- Journal
- International Journal on Semantic Web and Information Systems
- Published
- 2024-11-29
- DOI
- https://doi.org/10.4018/ijswis.361772
- Citations
- 25
- Primary Topic
- Spam and Phishing Detection
- Type
- article
- Field-Weighted Citation Impact
- 19.48