AntiPhishStack: LSTM-based Stacked Generalization Model for Optimized Phishing URL Detection

TL;DR

AntiPhishStack is a novel two-phase deep learning model that combines LSTM, stacking, and meta-classification to improve phishing URL detection without relying on prior phishing-specific features, achieving high accuracy.

Contribution

The paper introduces AntiPhishStack, a unique stacked generalization model utilizing LSTM and feature symmetry, advancing phishing detection methods beyond traditional feature-based approaches.

Findings

Achieved 96.04% accuracy on benchmark datasets.

Demonstrated superior performance over existing phishing detection models.

Validated effectiveness of symmetrical feature learning in cybersecurity.

Abstract

The escalating reliance on revolutionary online web services has introduced heightened security risks, with persistent challenges posed by phishing despite extensive security measures. Traditional phishing systems, reliant on machine learning and manual features, struggle with evolving tactics. Recent advances in deep learning offer promising avenues for tackling novel phishing challenges and malicious URLs. This paper introduces a two-phase stack generalized model named AntiPhishStack, designed to detect phishing sites. The model leverages the learning of URLs and character-level TF-IDF features symmetrically, enhancing its ability to combat emerging phishing threats. In Phase I, features are trained on a base machine learning classifier, employing K-fold cross-validation for robust mean prediction. Phase II employs a two-layered stacked-based LSTM network with five adaptive optimizers for dynamic compilation, ensuring premier prediction on these features. Additionally, the symmetrical predictions from both phases are optimized and integrated to train a meta-XGBoost classifier, contributing to a final robust prediction. The significance of this work lies in advancing phishing detection with AntiPhishStack, operating without prior phishing-specific feature knowledge. Experimental validation on two benchmark datasets, comprising benign and phishing or malicious URLs, demonstrates the model's exceptional performance, achieving a notable 96.04% accuracy compared to existing studies. This research adds value to the ongoing discourse on symmetry and asymmetry in information security and provides a forward-thinking solution for enhancing network security in the face of evolving cyber threats.