Imagem da capa

A Hybrid Classical-Quantum Neural Network Model for DDoS Attack Detection in Software-Defined Vehicular Networks

Na minha lista:
Publicado no:Information vol. 16, no. 9 (2025), p. 722-739
Autor principal: Sarvade, Varun P
Outros Autores: Kulkarni Shrirang Ambaji, Vidya, Raj C
Publicado em:
MDPI AG
Assuntos:
Machine learning
Quantum computing
Software
Datasets
Accuracy
Quantum physics
Cluster analysis
Neural networks
Intrusion detection systems
Clustering
Support vector machines
Cybersecurity
Circuits
Denial of service attacks
Vehicles
Controllers
Entropy
Vector quantization
Efficiency
Acesso em linha:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
Resumo:A typical Software-Defined Vehicular Network (SDVN) is open to various cyberattacks because of its centralized controller-based framework. A cyberattack, such as a Distributed Denial of Service (DDoS) attack, can easily overload the central SDVN controller. Thus, we require a functional DDoS attack recognition system that can differentiate malicious traffic from normal data traffic. The proposed architecture comprises hybrid Classical-Quantum Machine Learning (QML) methods for detecting DDoS threats. In this work, we have considered three different QML methods, such as Classical-Quantum Neural Networks (C-QNN), Classical-Quantum Boltzmann Machines (C-QBM), and Classical-Quantum K-Means Clustering (C-QKM). Emulations were conducted using a custom-built vehicular network with random movements and varying speeds between 0 and 100 kmph. Also, the performance of these QML methods was analyzed for two different datasets. The results obtained show that the hybrid Classical-Quantum Neural Network (C-QNN) method exhibited better performance in comparison with the other two models. The proposed hybrid C-QNN model achieved an accuracy of 99% and 90% for the UNB-CIC-DDoS dataset and Kaggle DDoS dataset, respectively. The hybrid C-QNN model combines PennyLane’s quantum circuits with traditional methods, whereas the Classical-Quantum Boltzmann Machine (C-QBM) leverages quantum probability distributions for identifying anomalies.
ISSN:2078-2489
DOI:10.3390/info16090722
Fonte:Advanced Technologies & Aerospace Database