ABSTRACT
Intrusion detection system (IDS) is a significant mechanism to improve network security. As a promising technique, machine learning (ML) methods has been applied in IDS to obtain high classification accuracy. However, classical ML based IDS methods hit a bottleneck in computing performance in case of huge network traffic and complex high-dimensional data. Due to the parallelism, superposition, entanglement of quantum computing, quantum computing provides a new solution to speed up the classical ML algorithms. This paper proposes a novel IDS scheme based on full-rotation quantum convolutional neural network (FR-QCNN). The key component of the FR-QCNN is the quantum convolution filter, which is composed of coding layer, variational layer and measurement layer. Different from the traditional quantum convolutional neural network, a full-rotation quantum circuit is used in the variational layer of the FR-QCNN, realizing a complete parameter update in the model training. Experiment on dataset from KDD Cup shows that the IDS classification accuracy of FR-QCNN is higher than classical ML models such as convolutional neural network (CNN), decision tree (DT) and support vector machine (SVM), as well as higher than traditional quantum convolutional neural network(QCNN). Meanwhile, FR-QCNN and QCNN have lower space complexity and time complexity than classical ML methods.
- Grover, Lov K . Fixed-Point Quantum Search[J]. Physical Review Letters, 2005, 95(15):150501.Google ScholarCross Ref
- Yoder T J , Low G H , Chuang I L . Fixed-Point Quantum Search with an Optimal Number of Queries[J]. Physical Review Letters, 2014, 113(21):210501.Google ScholarCross Ref
- Mitchell T M . Machine Learning[M]. McGraw-Hill, 2003.Google Scholar
- Nooripour R , Hosseinian S , Hussain A J , How Resiliency and Hope Can Predict Stress of Covid-19 by Mediating Role of Spiritual Well-being Based on Machine Learning[J]. Journal of Religion and Health, 2021(1):1-16.Google Scholar
- Lloyd S , Mohseni M , Rebentrost P . Quantum principal component analysis[J]. Nature Physics, 2014, 10(9):108-113 vol. 1.Google ScholarCross Ref
- Ma W P . A novel quantum neural network based on multi-level activation function[J]. Laser Physics Letters, 2021, 18(2):025201 (7pp).Google ScholarCross Ref
- Sukumar J , Pranav I , Neetish M M , Network Intrusion Detection Using Improved Genetic k-means Algorithm[C]// 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI). 2018.eley.Google Scholar
- Boukhris I , Elouedi Z , Ajabi M . Toward intrusion detection using belief decision trees for big data[J]. Knowledge & Information Systems, 2017.Google ScholarDigital Library
- Kang S , Liu L , Liu C , Intrusion detection based on multiple layer extreme learning machine[J]. Journal of Computer Applications, 2015.Google Scholar
- Tarek, M, Taha, Intrusion Detection Using Deep Belief Network and Extreme Learning Machine[J]. International Journal of Monitoring and Surveillance Technologies Research, 2015, 3(2):35-56.Google ScholarDigital Library
- Mirza A H , Cosan S . Computer network intrusion detection using sequential LSTM Neural Networks autoencoders[C]// 2018:1-4.Google Scholar
- Li G. Research on Network Intrusion Detection Model Based on Quantum Artificial Fish Swarm and Fuzzy Kernel Clustering Algorithm [J]. Software Engineering, 2019, 22(06): 33-37.Google Scholar
- Zhang Z F. Feature Selection for Network Intrusion Detection Based on Quantum Evolutionary Algorithm [J]. Computer Applications, 2013, 33(05):1357-1361.Google ScholarCross Ref
- Liu X M . Research of Intrusion Detection Based on Fuzzy Clustering and the Quantum Genetic Theory[J]. Journal of Kaifeng University, 2011.Google Scholar
- Xu Lei, Li Yongzhong, Li Zhengjie, Network Intrusion Detection Algorithm Based on Quantum Particle Swarm Optimization [J]. Computer Engineering and Applications, 2011, 47(36):4.Google Scholar
- Zz A , Dc A , Jw C , Quantum-based subgraph convolutional neural networks[J]. Pattern Recognition, 2019, 88:38-49.Google ScholarDigital Library
- Killoran N , Bromley T R , Arrazola J M , Continuous-variable quantum neural networks[J]. Physical Review Research, 2019, 1(3).Google ScholarCross Ref
- Liu H Y , Sun T P , Wu Y C , Variational Quantum Algorithms for the Steady States of Open Quantum Systems[J]. Chinese Physics Letters, 2021, 38(8):080301 (6pp).Google ScholarCross Ref
- Soklakov A N , Schack R . Efficient state preparation for a register of quantum bits[J]. Phys.rev.a, 2006, 73(1):5689-5693.Google Scholar
- Siddiqui M K , Naahid S . Analysis of KDD CUP 99 Dataset using Clustering based Data Mining[J]. International Journal of Database Theory & Application, 2013, 6(5):23-34.Google ScholarCross Ref
- Mitrofanov S A , Semenkin E S . Tree retraining in the decision tree learning algorithm[J]. IOP Conference Series: Materials Science and Engineering, 2021, 1047(1):012082 (7pp).Google ScholarCross Ref
- Hamada K , Ikarashi D , Kikuchi R , Efficient decision tree training with new data structure for secure multi-party computation[J]. 2021.Google Scholar
Index Terms
- Full-Rotation Quantum Convolutional Neural Network for Abnormal Intrusion Detection System
Recommendations
Amplitude transformed quantum convolutional neural network
AbstractWith the rapid development of quantum neural networks (QNN), several quantum simulations of convolutional neural networks (CNN) have been proposed. Among them, Google has proposed three quantum convolutional neural network (QCNN) models, but its ...
RGB image classification with quantum convolutional ansatz
AbstractWith the rapid growth of qubit numbers and coherence times in quantum hardware technology, implementing shallow neural networks on the so-called Noisy Intermediate-Scale Quantum (NISQ) devices has attracted a lot of interest. Many quantum (...
Network Intrusion Detection System Using Neural Networks
ICNC '08: Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 05This paper presents a neural network-based intrusion detection method for the internet-based attacks on a computer network. Intrusion detection systems (IDS) have been created to predict and thwart current and future attacks. Neural networks are used to ...
Comments