Litcius/Paper detail

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

Liang Zhou, Akshat Gaurav, Varsha Arya, Razaz Waheeb Attar, Shavi Bansal, Ahmed Alhomoud

2024International Journal on Semantic Web and Information Systems26 citationsDOIOpen Access PDF

Abstract

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.

Topics & Concepts

Computer scienceWorld Wide WebPhishingArtificial intelligenceSemantic WebDeep WebInformation retrievalSemantic Web StackNatural language processingDeep learningSocial Semantic WebThe InternetSpam and Phishing DetectionSentiment Analysis and Opinion MiningNetwork Security and Intrusion Detection
Enhancing Phishing Detection in Semantic Web Systems Using Optimized Deep Learning Models | Litcius