Special lssues
Table of Content

Machine Learning for Cybersecurity in Quantum Era Threats, Challenges, and Opportunities

Submission Deadline: 31 October 2022 (closed)

Guest Editors

Dr. Fahad Ahmad, Jouf University, Saudi Arabia.
Dr. Iftikhar Hussain, Heriot-Watt University, UK.
Dr. Shahid Naseem, University of Education, Pakistan.


Machine learning has been a subject of increasing concern to scholars, both from academia and enterprises, over the past few years. Unlike conventional learning methods, machine learning methods suggest the potential to learn and develop very broad sets of data. Machine learning methods in cybersecurity, natural language analysis, robots, and other fields have gained considerable popularity in numerous activities. Recent years have seen a tremendous advancement of the principle of machine learning and numerous implementations in the general area of artificial intelligence, including neural network architecture, automation, statistical analysis and deep learning.

Though machine learning has been extensively explored in recent decades, the use of machine learning strategies in intelligent systems faces several complexities. Well first of all, machine learning methods need a vast and varied amount of data as input to frameworks and require a wide range of training requirements. Secondly, the teaching of machine learning models is quick to slip into overfitting issues. Furthermore, because machine learning systems have uncertainty or backbox problems, it is challenging to consider how a given algorithm makes a judgment, which is essential in certain fields such as cybersecurity, network management and cryptography.

The development of quantum technologies opens a new era for cyber security, with new threats and new possibilities rapidly emerging. For example, the prospect of scalable quantum computers, with the ability to break hard problems commonly used by cryptosystems, would compromise the security of our communications or networks. At the same time, the development of quantum communication networks could offer an infrastructure where theoretically secure communication protocols (such as encryption) can be realized, sidestepping the aforementioned threat. While the above examples are important, the range of cyber security applications affected by quantum technologies is much greater. One can envision that, in the foreseeable future, we will have communication and computation networks composed of both classical and quantum devices of variable power from IoT sensors to supercomputers and universal quantum computers, all interconnected in a large hybrid quantum–classical network.

The focus of this Special Issue will cover all aspects of research addressing the security and enhanced performance of the future hybrid classical–quantum communication and computation networks through machine learning techniques.


• cybersecurity and AI
• quantum key distribution
• secure quantum computing
• quantum cryptanalysis
• quantum hacking
• quantum Internet
• device-independent cryptography
• quantum communication
• quantum complexity theory
• quantum cryptography
• quantum games
• quantum information processing (QIP)
• quantum networks
• quantum programing
• quantum algorithms
• quantum computing
• quantum IoT (QIoT)
• quantum software defined network (QSDN)
• quantum network virtualization function (QNVF)
• quantum next generation networks (QNGN)
• quantum key distribution (QKD)
• quantum random number generators (QRNG)
• quantum signatures
• secure cloud quantum computation
• quantum security multi party communication (QSPMC)
• quantum 4g/5g communication
• quantum internet
• quantum blockchain (QBC)
• quantum e-voting
• quantum money
• quantum cryptanalysis
• relativistic quantum cryptography
• device-independent protocols
• quantum hacking

Share Link