Intelligent Security for Phishing Online using Adaptive Neuro Fuzzy Systems

Abstract

Anti-phishing detection solutions employed in industry use blacklist-based approaches to achieve low false-positive rates, but blacklist approaches utilizes website URLs only. This study analyses and combines phishing emails and phishing web-forms in a single framework, which allows feature extraction and feature model construction. The outcome should classify between phishing, suspicious, legitimate and detect emerging phishing attacks accurately. The intelligent phishing security for online approach is based on machine learning techniques, using Adaptive Neuro-Fuzzy Inference System and a combination sources from which features are extracted. An experiment was performed using twofold cross validation method to measure the system's accuracy. The intelligent phishing security approach achieved a higher accuracy. The finding indicates that the feature model from combined sources can detect phishing websites with a higher accuracy. This paper contributes to phishing field a combined feature which sources in a single framework. The implication is that phishing attacks evolve rapidly; therefore, regular updates and being ahead of phishing strategy is the way forward.