Quantum Anomaly Detection for Advanced Persistent Threats Using Quantum Support Vector Machines

Jaideep Rukmangadan, Seema Vasudevan

2025

Abstract

Cyber threat sophistication, in particular Advanced Persistent Threats (APTs), requires new detection technologies to deal with big and encrypted data. Anomaly detection has become an unsustainable process in big data environments with encryption making them even more so. This article presents a new method utilizing QSVM (Quantum Support Vector Machines) and Quantum Kernel Methods to find out anomalies in encrypted communication paths. Quantum kernels can translate input information into higher-dimensional Hilbert spaces, with computational efficiency and precision over and above that of the classical methods. The use of QSVM can detect faint signals from APTs (like Zero-Day attacks) more accurately. This paper also tests the security of encryption protocols such as RSA and AES on quantum simulators and proposes quantum-safe alternatives to protect against quantum attacks before they happen. Experimental findings show significant enhancements in anomaly detection performance and computation speed, which are a first of their kind for quantum-based cybersecurity systems.

Paper Citation

in Harvard Style

Rukmangadan J. and Vasudevan S. (2025). Quantum Anomaly Detection for Advanced Persistent Threats Using Quantum Support Vector Machines. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 261-266. DOI: 10.5220/0013896400004919

in Bibtex Style

@conference{icrdicct`2525,
author={Jaideep Rukmangadan and Seema Vasudevan},
title={Quantum Anomaly Detection for Advanced Persistent Threats Using Quantum Support Vector Machines},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={261-266},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013896400004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Quantum Anomaly Detection for Advanced Persistent Threats Using Quantum Support Vector Machines
SN - 978-989-758-777-1
AU - Rukmangadan J.
AU - Vasudevan S.
PY - 2025
SP - 261
EP - 266
DO - 10.5220/0013896400004919
PB - SciTePress