Phishing threat mitigation in E-commerce using a quantum-enhanced hybrid AI framework

Phishing websites continue to pose a significant cybersecurity threat, exploiting URL structures to deceive users and bypass traditional detection systems. Most existing models rely solely on classical deep learning, which often incurs high computational overhead and lacks interpretability. In this context, this paper proposes a quantum-enhanced hybrid AI model that integrates a classical neural encoder with a parameterized quantum circuit, leveraging quantum entanglement and superposition for enriched feature representation. The model processes URL-based features and achieves a classification accuracy of 97.3% with significantly reduced trainable parameters compared to baseline methods. The results confirm the model's effectiveness, efficiency, and potential in next-generation phishing detection systems.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2025-11-27
DOI
https://doi.org/10.1038/s41598-025-27515-7
Primary Topic
Spam and Phishing Detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Phishing threat mitigation in E-commerce using a quantum-enhanced hybrid AI framework

Shin‐Hung Pan, Razaz Waheeb Attar, Akshat Gaurav, Hassan A. Alhazmi et al.
Scientific Reports
Spam and Phishing Detection
article

Phishing threat mitigation in E-commerce using a quantum-enhanced hybrid AI framework

Shin‐Hung Pan, Razaz Waheeb Attar, Akshat Gaurav, Hassan A. Alhazmi, Brij B. Gupta, Kwok Tai Chui, Varsha Arya, Ahmed Alhomoud
article en

Abstract

Phishing websites continue to pose a significant cybersecurity threat, exploiting URL structures to deceive users and bypass traditional detection systems. Most existing models rely solely on classical deep learning, which often incurs high computational overhead and lacks interpretability. In this context, this paper proposes a quantum-enhanced hybrid AI model that integrates a classical neural encoder with a parameterized quantum circuit, leveraging quantum entanglement and superposition for enriched feature representation. The model processes URL-based features and achieves a classification accuracy of 97.3% with significantly reduced trainable parameters compared to baseline methods. The results confirm the model's effectiveness, efficiency, and potential in next-generation phishing detection systems.

Scientific ReportsVol. 15(1)
Chandigarh University (IN), Princess Nourah bint Abdulrahman University (SA), Northern Border University (SA), Chaoyang University of Technology (TW), Asia University (TW), China Medical University (TW), Symbiosis International University (IN), Korea Soongsil Cyber ​​University (KR), China Medical University Hospital (TW), Ronin Institute (US), University of Warsaw (PL), University of Petroleum and Energy Studies (IN)
Princess Nourah Bint Abdulrahman University
Openalex Percentile: Top 50%
Spam and Phishing Detection
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.