Current digital networks face more advanced cybersecurity threats because interconnected digital systems that
comprise cyber-physical systems and cloud computing and the Internet of Things (IoT) have become widely adopted. The
traditional cybersecurity systems which depend on basic computer techniques and process data through one thread cannot
protect systems against ongoing advanced threats and developing malware and newly discovered system vulnerabilities. The
Quantum-Enhanced Cyber Defence System (QE-CDS) develops its cyber defence system by combining quantum computing
with artificial intelligence and machine learning and large language models. The suggested framework employs Quantum
Machine Learning (QML) methods through its Quantum Support Vector Machines (QSVM) and Quantum Neural Networks
(QNN) and Quantum Recurrent Neural Networks (QRNN) and Quantum Approximate Optimization Algorithms (QAOA).
Scientists conducted their research through a hybrid quantum-classical simulation environment which used benchmark
datasets like CICIDS2017 and UNSW-NB15 and Bot-IoT. Our system outperforms standard systems in detecting threats
because it identifies threats more quickly and makes superior defensive choices and finishes detection work with less than
standard false positive rates and operates more effectively in large environments. The security analysis of unstructured data
becomes more precise through the integration of Large Language Models with cybersecurity systems that use quantum
computing technology. The simulation results show that future security systems will be developed through hybrid systems
which combine quantum technology with artificial intelligence because these systems can adapt to emerging threats while
defending against quantum attacks.
[1] Ajimon, Kumar 2024 Anomaly detecting quantum + llms. Absence of real-time and smart detection Innovations in
Information Security, Privacy and Ethics.
[2] Azeez et al. 2024 Cyber threat detection quantum models Classical models are too slow to be useful with complex threats
International Journal of Science and Research Archive
[3] Thirupathi et al. 2024 Quantum AI-based cybersecurity Lack of synergy between AI and quantum Developments in
Mechatronics and Mechanical Engineering
[4] Hossain et al. 2024 QMLto detect, in real-time Slow and erroneous detection systems RTIC - Revista
de Tecnologies, Informacion Comunication.
[5] Deepajothi et al. 2024 Adaptive security with quantum ML Classical ML unable to adapt to changing threats Computer
and Electrical Engineering Developments
[6] Shamoo 2024 LLM + quantum in autonomous defence With static systems, threats cannot be responded to. Innovations
in Information Security, Privacy, and Ethics.
[7] Ramya et al. 2024 NLP of cyber threats quantum based NLP cannot deal with complex cyber-language Insurance
Cybersecurity and Information Management Journal
[8] Alluhaibi 2024 QML improves preventive threat detection ML stiff to new threat patterns International Journal of Safety
Engineering and Security
[9] Shaik et al. 2024 ML in resistance against networks caused by quantum ML is also incapable of dealing with
sophisticated network intrusions Int. Journal of Advanced Research in science, communication and technology
[10] Albtosh 2024 Quantum-sensitive LLMs for incident response Lack of dynamic adaptation in systems Progress in
Information Security, Privacy, and Ethics
[11] Rosa-Remedios, Caballero-Gil 2024 Proactive QML models for threat detection Existing models are reactive
Optimization and Engineering
[12] Abreu et al. 2024 QML-IDS improves detection speed vs classical IDS Classical IDS too slow with large traffic Int.
Intelligent Computing and Artificial Intelligence Conference
[13] Tehrani et al. 2024 Quantum SIEM is efficient and quick in identifying a botnet Traditional SIEM lacked responsiveness
Science Reports
[14] Knaapen et al. 2024 Ransomware detection using quantum entropy model Difficult to detect morphing ransomware
Research Square
[15] Yadav et al. 2023 QNN & QSVM improve the detection of the threat. Slow rate and accuracy of DL models ICRASET
Proceedings
[16] Payares & MartÃnez-Santos 2023 Survey of QML for IDS IDS lacks speed and scale Digital Crime, Forensics and Cyber
Terrorism
[17] Kiyatake Nicesio et al. 2023 Review: QML improves NIDS performance Lack of evaluation in QML for NIDS Int.
Conf. on AI and Communication Technology
[18] S. Aggarwal et al. 2023 Quebec computing Overview The critical issues of distribution and entanglement Innovations in
Systems Analysis, Software Engineering, and High Performance computing.
[19] K. S. Divyashree 2023 Quantum threats, safe algos Systems not quantum-ready Quantum Computing Era: Security and
Applications
[20] Hussain et al. 2021 AI + quantum for scalable detection Classical systems not scalable to big data World Journal of
Advanced Research and Reviews
