Cyber attacks on data servers and critical infrastructure of fifth-generation (5G) wireless communication networks are increasing day by day. Therefore, an intelligent, reliable and cost effictive security of sixth-generation (6G) wireless communication network is inevitable. Quantum technology is one of the enabling technologies of future computing, as well as of the 6G. In the event of a cyberattack, rapid response is critical to minimize the risk of data loss and denial-of-service (DoS) attacks. Quantum computers are a new generation of computers that are expected to be much faster than classical computers. In this study, we have proposed and implemented a hybrid quantum neural network (HQNN) model. The proposed HQNN model was trained and tested on a dataset from the Australian center for cybersecurity. Simulation results show that the proposed HQNN model is faster in training as well as in the testing phase compared to classical neural networks. Moreover, our proposed model helps to overcome the underutilization of centeral processing unit (CPU) resources. CPU utilization of our proposed HQNN model is 95-100%, while that of the classical model is only 35-75% during the training and testing of the dataset.
Cyber attacks on data servers and critical infrastructure of fifth-generation (5G) wireless communication networks are increasing day by day. Therefore, an intelligent, reliable and cost effictive security of sixth-generation (6G) wireless communication network is inevitable. Quantum technology is one of the enabling technologies of future computing, as well as of the 6G. In the event of a cyberattack, rapid response is critical to minimize the risk of data loss and denial-of-service (DoS) attacks. Quantum computers are a new generation of computers that are expected to be much faster than classical computers. In this study, we have proposed and implemented a hybrid quantum neural network (HQNN) model. The proposed HQNN model was trained and tested on a dataset from the Australian center for cybersecurity. Simulation results show that the proposed HQNN model is faster in training as well as in the testing phase compared to classical neural networks. Moreover, our proposed model helps to overcome the underutilization of centeral processing unit (CPU) resources. CPU utilization of our proposed HQNN model is 95-100%, while that of the classical model is only 35-75% during the training and testing of the dataset.
The cybersecurity is confronted with new challenges due to the increase in cyberattacks in terms of their cleverness, speed, and lack of detection. The traditional security systems tend to be slow in countering the sophisticated attacks. Simultaneously, quantum computing is establishing opportunities and risks in regards to security. The paper reviews the literature on quantum computing and machine learning as approaches to enhancing cybersecurity and also explores the difficulties arising with quantum technologies. The paper is conducted based on the PRISMA framework to conduct the search, filtering, the assessment, and synthesis of recent studies on key scientific databases. According to the results hybrid quantum-classical computing and Quantum Neural Networks can enhance intelligent threat detection, predictive analytics, cyber risk assessment, security automation and autonomous security systems. The analysis also shows some key weaknesses, such as the lack of quantum hardware, quantum error correction issues, high computations, the absence of standard security frameworks, privacy issues, and the paucity of practical deployed research. The paper emphasizes that machine learning and quantum computing used together would make cyber resilience, aiding secure computing, enhancing digital forensic, and speeding up further cybersecurity innovation. It is; the review concludes that future studies in Energy in Quantum Security, Quantum-Resistant Security, Zero Trust Security and intelligent cyber defense systems will be important in creating safe, all-scale, and responsive cybersecurity infrastructures in the digitalized environment of the future.
As fifth-generation (5G) and next-generation communication systems advance and find widespread application in critical infrastructures, the importance of vulnerability detection becomes increasingly critical. The growing complexity of these systems necessitates rigorous testing and analysis, with stringent requirements for both accuracy and speed. In this article, we present a state-of-the-art supervised hybrid quantum neural network named HyQ2 for vulnerability detection in next-generation wireless communication systems. The proposed HyQ2 is integrated with graph-embedded and quantum variational circuits to validate and detect vulnerabilities from the 5G system's state transitions based on graphs extracted from log files. We address the limitations of classical machine learning models in processing the intrinsic linkage relationships of high-dimensional data. These models often suffer from dead neurons and excessively large outputs caused by the unbounded range of the rectified linear unit (ReLU) activation function. We propose the HyQ2 method to overcome these challenges, which constructs quantum neurons by selecting random neurons' outputs from a classical neural network. These quantum neurons are then utilized to capture more complex relationships, effectively limiting the ReLU output. Using only two qubits, our validation results demonstrate that HyQ2 outperforms traditional classical machine learning models in vulnerability detection. The small and compact variational circuit of HyQ2 minimizes the noise and errors in the measurement. Our results demonstrate that HyQ2 achieves a high area under the curve (AUC) value of 0.9708 and an accuracy of 95.91%. To test the model's performance in quantum noise environments, we simulate quantum noise by adding bit flipping, phase flipping, amplitude damping, and depolarizing noise. The results show that the prediction accuracy and receiver operating characteristic AUC value fluctuate around 0.2%, indicating HyQ2’s robustness in noisy quantum environments. In addition, the noise resilience and robustness of the HyQ2 algorithm were substantiated through experiments on the IBM quantum machine with only a 0.2% decrease compared to the simulation results.
Wireless communication systems face increasing challenges in resource allocation, latency reduction, scalability, and adaptation because modern networks generate high-dimensional, nonlinear, and rapidly changing data. This work presents a hybrid Quantum Neural Network (QNN)-driven framework for intelligent resource optimization in dynamic wireless communication environments. The proposed framework integrates variational quantum circuits with classical optimization techniques to support adaptive learning and efficient decision-making. A modular architecture consisting of User, Database, and Operator modules enables secure data acquisition, storage, preprocessing, continuous model training, and operator-driven optimization. Quantum Neural Networks are employed as the primary learning mechanism, while hybrid quantum-classical optimization supports stable parameter training. Quantum annealing is incorporated for complex tasks such as channel allocation, bandwidth management, and resource scheduling. The framework is designed to improve allocation accuracy, reduce latency, enhance scalability, reliability, security, and resource utilization. Continuous learning further enables adaptation to changing traffic patterns, user requirements, workloads, and network conditions. Keywords: Quantum Neural Network, Wireless Communication, Resource Optimization, Quantum Computing, Hybrid Quantum-Classical Learning, Resource Allocation.
In this paper, it talks about integrating hybrid quantum-classical communication networks to enhance the measures for cybersecurity. Traditional security frameworks come under severe strain with ever-advancing threats in the cyber world. With this regard, we propose a new architecture that brings the paradigm of quantum cryptography and classical protocols to provide secure data transfer along with enhancing the system's resilience towards attacks. The intense simulation carried out greatly reduced the incidence of data breaches by 45% relative to classical-only systems, and encryption speed is improved by 60% through quantum key distribution. On the other side, our hybrid has resulted in 35% network throughput increase without high latency. Overall, such research points towards the potential to address current vulnerabilities of cybersecurity infrastructures by using quantum technology. Thus, the bottom line is that interdisciplinary collaboration provides the route to the development of reliable security solutions, especially in this very dynamic digital world. We look forward to further work relating to the actual implementation of the optimized hybrid systems that we developed for these environments.
The upcoming fifth generation (5G) of wireless networks is expected to lay a foundation of intelligent networks with the provision of some isolated artificial intelligence (AI) operations. However, fully intelligent network orchestration and management for providing innovative services will only be realized in Beyond 5G (B5G) networks. To this end, we envisage that the sixth generation (6G) of wireless networks will be driven by on-demand self-reconfiguration to ensure a many-fold increase in the network performance and service types. The increasingly stringent performance requirements of emerging networks may finally trigger the deployment of some interesting new technologies, such as large intelligent surfaces, electromagnetic-orbital angular momentum, visible light communications, and cell-free communications, to name a few. Our vision for 6G is a massively connected complex network capable of rapidly responding to the users' service calls through real-time learning of the network state as described by the network edge (e.g., base-station locations and cache contents), air interface (e.g., radio spectrum and propagation channel), and the user-side (e.g., battery-life and locations). The multi-state, multi-dimensional nature of the network state, requiring the real-time knowledge, can be viewed as a quantum uncertainty problem. In this regard, the emerging paradigms of machine learning (ML), quantum computing (QC), and quantum ML (QML) and their synergies with communication networks can be considered as core 6G enablers. Considering these potentials, starting with the 5G target services and enabling technologies, we provide a comprehensive review of the related state of the art in the domains of ML (including deep learning), QC, and QML and identify their potential benefits, issues, and use cases for their applications in the B5G networks. Subsequently, we propose a novel QC-assisted and QML-based framework for 6G communication networks while articulating its challenges and potential enabling technologies at the network infrastructure, network edge, air interface, and user end. Finally, some promising future research directions for the quantum- and QML-assisted B5G networks are identified and discussed.
Quantum Neural Network (QNN) provides an exciting alternative to machine learning as they take advantage of quantum computer properties when making decisions and processing data. However, the integration of high-dimensional classical data with the limited number of qubits available on current Noisy Intermediate-Scale Quantum computers presents a major difficulty. This paper presents a complete hybrid quantum-classical architecture in Qiskit that utilizes the Network Security Laboratory-Knowledge Discovery and Data Mining (NSL-KDD) dataset to classify network intrusions among multiple classes. In order to work around the exponential cost of computations and reduce the number of times quantum circuits need to be run due to hardware limitations, a subset of the dataset will be created to use during both training and testing. The architecture proposed in this paper uses a four-qubit Variational Quantum Circuit (VQC). First, a classical feature vector is used to create a quantum Hilbert space via a ZZFeatureMap, which initializes the qubits via a Hadamard transformation followed by phase rotation gates that create controlled-entanglement between pairs of features. The quantum states are then passed through a RealAmplitudes variational circuit, while the classical layer optimizes the parameters using the Constrained Optimization BY Linear Approximations (COBYLA) algorithm. The overall accuracy of the model when tested on five classes of intrusion detection results in an accuracy level of 59%, with very strong classification accuracies for both Denial of Service (DoS) and User-to-Root (U2R) attacks as demonstrated by their F1 scores. The proposed QNN achieves a highly competitive baseline of 86% accuracy and 86% recall in specific configurations. These results underscore the potential of shallow, lower-complexity QNN architectures as an emergent tool for cybersecurity in the quantum era.