PhishVQC: Optimizing Phishing URL Detection with Correlation Based Feature Selection and Variational Quantum Classifier

2025-03-03

AI Summary

To address the limited generalization capability of traditional machine learning methods for phishing URL detection under large-scale, high-noise, and few-shot conditions, this paper proposes the first classical-quantum hybrid approach tailored to cybersecurity tasks. Our method integrates Pearson correlation coefficient-based feature selection with a variational quantum classifier (VQC), employing RealAmplitude and EfficientSU2 quantum circuits to perform quantum feature mapping and discriminative learning on high-dimensional URL patterns. This work represents the first systematic application of quantum feature mapping and VQC to phishing URL detection. Evaluated on standard benchmarks, it achieves a macro-averaged F1-score of 0.89—outperforming the current state-of-the-art by 22%—while demonstrating significantly improved robustness and generalization. The results empirically validate the feasibility and practical potential of quantum machine learning in real-world security applications.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Phishing URL detection is crucial in cybersecurity as malicious websites disguise themselves to steal sensitive infor mation. Traditional machine learning techniques struggle to per form well in complex real-world scenarios due to large datasets and intricate patterns. Motivated by quantum computing, this paper proposes using Variational Quantum Classifiers (VQC) to enhance phishing URL detection. We present PhishVQC, a quantum model that combines quantum feature maps and vari ational ansatzes such as RealAmplitude and EfficientSU2. The model is evaluated across two experimental setups with varying dataset sizes and feature map repetitions. PhishVQC achieves a maximum macro average F1-score of 0.89, showing a 22% improvement over prior studies. This highlights the potential of quantum machine learning to improve phishing detection accuracy. The study also notes computational challenges, with execution wall times increasing as dataset size grows.

Problem

• Enhance phishing URL detection using quantum computing techniques.
• Address limitations of traditional machine learning in complex datasets.
• Improve accuracy with Variational Quantum Classifiers and feature selection.

Innovation

• Uses Variational Quantum Classifiers for phishing detection
• Combines quantum feature maps with variational ansatzes
• Achieves 22% improvement in detection accuracy