A Hybrid Framework Integrating QML, AI, and Quantum-Safe Cryptography for Cybersecurity
Open Access
- 3 September 2025
- journal article
- Published by BON VIEW PUBLISHING PTE in Journal of Computational and Cognitive Engineering
- Vol. 5 (1) , 16-29
Abstract
The rise of quantum computing poses threats to traditional cryptographic systems, thereby requiring security measures to safeguard against traditional and quantum-attacker cyber insecurity. This framework uses quantum machine learning (QML) algorithms along with quantum-safe encryption to boost security measures. The proposed system combines QML anomaly detection models variational quantum classifier (VQC) with quantum support vector classifier (QSVC) as well as quantum neural network and examines them based on the BB84 QKD protocol for information safety. This model was evaluated using three datasets of HIKARI Flow intrusion detection records, phishing activity logs, and malicious URLs. This includes all high-dimensional input by extensive application of feature engineering, which merges entropy scoring combined with keyword extraction and domain analysis to transmogrify it into suitable inputs for quantum processing. The QML models outperformed the traditional models with a maximum phishing detection accuracy of 97.75% by QSVC implementation. With the BB84 protocol, its eavesdropping detection was proved by quantum interference detection upon testing on IBM's Qiskit and Google's Cirq systems while the operations were secure and in attack scenarios. This system combines the latest features to address the limitations of the current AI security model and incorporates post-quantum cryptography to protect against quantum threats. In conclusion, QML and quantum cryptography work efficiently with operational cybersecurity platforms. Received: 31 December 2024 | Revised: 10 April 2025 | Accepted: 7 May 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available from the corresponding author upon reasonable request. Author Contribution Statement Ramasubramaniyan Gunasridharan: Methodology. Ali Altalbe: Methodology. Bharathi Mohan Gurusamy: Conceptualization, Writing - review & editing. Gundala Pallavi: Writing - original draft. Prasanna Kumar Rangarajan: Supervision.Keywords
This publication has 39 references indexed in Scilit:
- Quantum machine learning: a systematic categorization based on learning paradigms, NISQ suitability, and fault toleranceQuantum Machine Intelligence, 2025
- Evaluating the potential of quantum machine learning in cybersecurity: A case-study on PCA-based intrusion detection systemsComputers & Security, 2025
- Optimizing quantum machine learning for proactive cybersecurityOptimization and Engineering, 2024
- A deep learning framework for automated anomaly detection and localization in fused filament fabricationManufacturing Letters, 2024
- Cryptographic CompetitionsJournal of Cryptology, 2023
- A roadmap from classical cryptography to post-quantum resistant cryptography for 5G-enabled IoT: Challenges, opportunities and solutionsInternet of Things, 2023
- Artificial intelligence for cybersecurity: Literature review and future research directionsInformation Fusion, 2023
- Security intrusion detection using quantum machine learning techniquesJournal of Computer Virology and Hacking Techniques, 2022
- GuardHealth: Blockchain empowered secure data management and Graph Convolutional Network enabled anomaly detection in smart healthcareJournal of Parallel and Distributed Computing, 2020
- Quantum speed-up for unsupervised learningMachine Learning, 2012