Back to all available

Phishing detection gets smarter: A novel quantum artificial intelligence approach with data fusion techniques

algorithms-and-analysis-of-algorithms
artificial-intelligence
security-and-privacy
quantum-computing
neural-networks

Abstract

Background. The Internet has become an essential tool for both individuals and businesses; however, its widespread use has also increased their vulnerability to cyberattacks. Classical Machine Learning (ML) models have been widely applied to binary phishing detection; however, the potential of Quantum Artificial Intelligence (QAI) in this area remains largely unexplored for multiclass phishing detection problems with a large and diverse number of features.

Methods. Unlike most existing binary phishing detection approaches, we address the more challenging problem of multiclass classification for phishing detection. We contribute in two main ways. First, we propose two novel QAI models: a Hybrid Quantum-Neural Network (HQNN), which combines classical neural networks with parameterized quantum circuits, and a Quantum Support Vector Machine (QSVM), which leverages quantum kernels to project data into higher-dimensional Hilbert spaces. Second, we integrate Data Fusion (DF) techniques to enrich feature representation, enabling effective learning from a relatively smaller dataset with many features.

Results. Experimental evaluation shows that HQNN and QSVM, when combined with DF, substantially outperform traditional ML baselines (XGBoost, AdaBoost, SVM, Random Forest). HQNN achieved 98% accuracy and QSVM 96%, both exceeding the performance of classical models. Integrating classical and quantum paradigms not only improved accuracy but also reduced model size and parameter requirements. Our findings highlight the value of combining QAI with DF techniques for robust and efficient phishing detection. Our proposed models demonstrate strong potential for industrial deployment in real-time cybersecurity, particularly in resource-constrained environments such as mobile devices.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].