An efficient intrusion detection model based on convolutional spiking neural network
Abstract Many intrusion detection techniques have been developed to ensure that the target system can function properly under the established rules. With the booming Internet of Things (IoT) applications, the resource-constrained nature of its devices makes it urgent to explore lightweight and high-...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-57691-x |
| _version_ | 1797233687644864512 |
|---|---|
| author | Zhen Wang Fuad A. Ghaleb Anazida Zainal Maheyzah Md Siraj Xing Lu |
| author_facet | Zhen Wang Fuad A. Ghaleb Anazida Zainal Maheyzah Md Siraj Xing Lu |
| author_sort | Zhen Wang |
| collection | DOAJ |
| description | Abstract Many intrusion detection techniques have been developed to ensure that the target system can function properly under the established rules. With the booming Internet of Things (IoT) applications, the resource-constrained nature of its devices makes it urgent to explore lightweight and high-performance intrusion detection models. Recent years have seen a particularly active application of deep learning (DL) techniques. The spiking neural network (SNN), a type of artificial intelligence that is associated with sparse computations and inherent temporal dynamics, has been viewed as a potential candidate for the next generation of DL. It should be noted, however, that current research into SNNs has largely focused on scenarios where limited computational resources and insufficient power sources are not considered. Consequently, even state-of-the-art SNN solutions tend to be inefficient. In this paper, a lightweight and effective detection model is proposed. With the help of rational algorithm design, the model integrates the advantages of SNNs as well as convolutional neural networks (CNNs). In addition to reducing resource usage, it maintains a high level of classification accuracy. The proposed model was evaluated against some current state-of-the-art models using a comprehensive set of metrics. Based on the experimental results, the model demonstrated improved adaptability to environments with limited computational resources and energy sources. |
| first_indexed | 2024-04-24T16:20:08Z |
| format | Article |
| id | doaj.art-a682b39deb0c4d14bf39c7364d5cfd36 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T16:20:08Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a682b39deb0c4d14bf39c7364d5cfd362024-03-31T11:15:31ZengNature PortfolioScientific Reports2045-23222024-03-0114112010.1038/s41598-024-57691-xAn efficient intrusion detection model based on convolutional spiking neural networkZhen Wang0Fuad A. Ghaleb1Anazida Zainal2Maheyzah Md Siraj3Xing Lu4Faculty of Computing, Universiti Teknologi MalaysiaCollege of Computing and Digital Technology, Birmingham City UniversityFaculty of Computing, Universiti Teknologi MalaysiaFaculty of Computing, Universiti Teknologi MalaysiaSchool of Data Science and Artificial Intelligence, Wenzhou University of TechnologyAbstract Many intrusion detection techniques have been developed to ensure that the target system can function properly under the established rules. With the booming Internet of Things (IoT) applications, the resource-constrained nature of its devices makes it urgent to explore lightweight and high-performance intrusion detection models. Recent years have seen a particularly active application of deep learning (DL) techniques. The spiking neural network (SNN), a type of artificial intelligence that is associated with sparse computations and inherent temporal dynamics, has been viewed as a potential candidate for the next generation of DL. It should be noted, however, that current research into SNNs has largely focused on scenarios where limited computational resources and insufficient power sources are not considered. Consequently, even state-of-the-art SNN solutions tend to be inefficient. In this paper, a lightweight and effective detection model is proposed. With the help of rational algorithm design, the model integrates the advantages of SNNs as well as convolutional neural networks (CNNs). In addition to reducing resource usage, it maintains a high level of classification accuracy. The proposed model was evaluated against some current state-of-the-art models using a comprehensive set of metrics. Based on the experimental results, the model demonstrated improved adaptability to environments with limited computational resources and energy sources.https://doi.org/10.1038/s41598-024-57691-xSpiking neural networkConvolutional neural networkIntrusion detectionCyber securityDeep learningArtificial intelligence |
| spellingShingle | Zhen Wang Fuad A. Ghaleb Anazida Zainal Maheyzah Md Siraj Xing Lu An efficient intrusion detection model based on convolutional spiking neural network Scientific Reports Spiking neural network Convolutional neural network Intrusion detection Cyber security Deep learning Artificial intelligence |
| title | An efficient intrusion detection model based on convolutional spiking neural network |
| title_full | An efficient intrusion detection model based on convolutional spiking neural network |
| title_fullStr | An efficient intrusion detection model based on convolutional spiking neural network |
| title_full_unstemmed | An efficient intrusion detection model based on convolutional spiking neural network |
| title_short | An efficient intrusion detection model based on convolutional spiking neural network |
| title_sort | efficient intrusion detection model based on convolutional spiking neural network |
| topic | Spiking neural network Convolutional neural network Intrusion detection Cyber security Deep learning Artificial intelligence |
| url | https://doi.org/10.1038/s41598-024-57691-x |
| work_keys_str_mv | AT zhenwang anefficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT fuadaghaleb anefficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT anazidazainal anefficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT maheyzahmdsiraj anefficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT xinglu anefficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT zhenwang efficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT fuadaghaleb efficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT anazidazainal efficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT maheyzahmdsiraj efficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork AT xinglu efficientintrusiondetectionmodelbasedonconvolutionalspikingneuralnetwork |