Enhancing Phishing Detection in Semantic Web Systems Using Optimized Deep Learning Models

Liang Zhou

doi:10.4018/IJSWIS.361772

Enhancing Phishing Detection in Semantic Web Systems Using Optimized Deep Learning Models

2024-11-29

0

OA

AI

DOI：10.4018/IJSWIS.361772

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Adaptive Differential Evolution (JADE)

Convolutional Neural Network (CNN)

E -Commerce Security

Phishing

Detection

Semantic Web

Enhancing Phishing Detection in Semantic Web Systems Using Optimized Deep Learning Models

Abstract

Journal

Organization