Network Anomaly Traffic Detection Using WGAN-CNN-BiLSTM in Big Data Cloud–Edge Collaborative Computing Environment
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reducednetwork bandwidth consumption, and improved the quality of service for user experience; however, it hasalso introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud–edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing withcomplex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deeplearningnetwork models. A lightweight deep-learning model was proposed to address these challenges. First,normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wassersteingenerative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviatesthe imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessedand expanded local data are used to fine-tune the trained model. This ensures that the data of each edge nodeare more consistent with the local characteristics, effectively improving the system's detection ability. In thedesigned lightweight deep learning network model, two sets of convolutional pooling layers of convolutionalneural networks (CNN) were used to extract spatial features. The bidirectional long short-term memorynetwork (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjustedthrough the attention mechanism, improving the model's ability to identify abnormal traffic features. Theproposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953,respectively, showing superior accuracy to other comparative models. The proposed lightweight deeplearning network model has good application prospects for anomaly traffic detection in cloud–edgecollaborative computing architectures.
Abstract
Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reducednetwork bandwidth consumption, and improved the quality of service for user experience; however, it hasalso introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud–edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing withcomplex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deeplearningnetwork models. A lightweight deep-learning model was proposed to address these challenges. First,normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wassersteingenerative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviatesthe imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessedand expanded local data are used to fine-tune the trained model. This ensures that the data of each edge nodeare more consistent with the local characteristics, effectively improving the system's detection ability. In thedesigned lightweight deep learning network model, two sets of convolutional pooling layers of convolutionalneural networks (CNN) were used to extract spatial features. The bidirectional long short-term memorynetwork (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjustedthrough the attention mechanism, improving the model's ability to identify abnormal traffic features. Theproposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953,respectively, showing superior accuracy to other comparative models. The proposed lightweight deeplearning network model has good application prospects for anomaly traffic detection in cloud–edgecollaborative computing architectures.
참고문헌 (35)
- C. Wang, "Multimodal semantic communication accelerated bidirectional caching for 6G MEC", Future Generation Computer Systems, 140, pp.225~237 (2023)[DOI]
- L. Li, "Resource allocation for NOMA-MEC systems in ultra-dense networks : a learning aided mean-field game approach", IEEE Transactions on Wireless Communications, 20(3), pp.1487~1500 (2021)[DOI]
- A. S. Almogren, "Intrusion detection in Edge-of-Things computing", Journal of Parallel and Distributed Computing, 137, pp.259~265 (2020)[DOI]
- X. Zhao, "Research on lightweight anomaly detection of multimedia traffic in edge computing", Computers & Security, 111 (2021)[DOI]
- "Wasserstein GAN" (2017)[URL]
- B. Riyaz, "A deep learning approach for effective intrusion detection in wireless networks using CNN", Soft Computing, 24, pp.17265~17278 (2020)[DOI]
- K. Jiang, "Network intrusion detection combined hybrid sampling with deep hierarchical network", IEEE Access, 8, pp.32464~32476 (2020)[DOI]
- I. Idrissi, "Toward a deep learning-based intrusion detection system for IoT against botnet attacks", IAES International Journal of Artificial Intelligence, 10(1), pp.110~120 (2021)[DOI]
- A. D. Smith, "Event detection in educational records : an application of big data approaches", International Journal of Business and Systems Research, 15(3), pp.271~291 (2021)[DOI]
- A. Amouri, "A machine learning based intrusion detection system for mobile Internet of Things", Sensors, 20(2) (2020)[DOI]
- R. Kumar, "A distributed intrusion detection system to detect DDoS attacks in blockchain-enabled IoT network", Journal of Parallel and Distributed Computing, 164, pp.55~68 (2022)[DOI]
- X. Jiang, "Abnormal network data mining model based on deep training learning", International Journal of Internet Protocol Technology, 13(4), pp.228~236 (2020)[DOI]
- A. Al, "STL-HDL : a new hybrid network intrusion detection system for imbalanced dataset on big data environment", Computers & Security, 110 (2021)[DOI]
- D. Tang, "A new detection method for LDoS attacks based on data mining", Future Generation Computer Systems, 128, pp.73~87 (2022)[DOI]
- J. Fei, "The abnormal detection for network traffic of power IoT based on device portrait", Scientific Programming, 2020 (2020)[DOI]
- S. J. Lee, "IMPACT : impersonation attack detection via edge computing using deep autoencoder and feature abstraction", IEEE Access, 8, pp.65520~65529 (2020)
- M. Eskandari, "Passban IDS : an intelligent anomaly-based intrusion detection system for IoT edge devices", IEEE Internet of Things Journal, 7(8), pp.6882~6897 (2020)[DOI]
- X. An, "Sample selected extreme learning machine based intrusion detection in fog computing and MEC", Wireless Communications and Mobile Computing, 2018 (2018)[DOI]
- L. F. Maimo, "A self-adaptive deep learning-based system for anomaly detection in 5G networks", IEEE Access, 6, pp.7700~7712 (2018)[DOI]
- B. Hussain, "Mobile edge computing-based data-driven deep learning framework for anomaly detection", IEEE Access, 7, pp.137656~137667 (2019)[DOI]
- B. Hussain, "Artificial intelligence-powered mobile edge computingbased anomaly detection in cellular networks", IEEE Transactions on Industrial Informatics, 16(8), pp.4986~4996 (2020)[DOI]
- C. A. De Souza, "Two-step ensemble approach for intrusion detection and identification in IoT and fog computing environments", Computers & Electrical Engineering, 98 (2022)[DOI]
- H. Bangui, "Lightweight intrusion detection for edge computing networks using deep forest and bio-inspired algorithms", Computers and Electrical Engineering, 100 (2022)[DOI]
- W. Zhong, "Applying big data based deep learning system to intrusion detection", Big Data Mining and Analytics, 3(3), pp.181~195 (2020)[DOI]
- S. Garg, "Statistical vertical reduction-based data abridging technique for big network traffic dataset", International Journal of Communication Systems, 33(4) (2020)[DOI]
- A. Abid, "Intrusion detection based on graph oriented big data analytics", Procedia Computer Science, 176, pp.572~581 (2020)[DOI]
- F. Jin, "Intrusion detection on internet of vehicles via combining log-ratio oversampling, outlier detection and metric learning", Information Sciences, 579, pp.814~831 (2021)[DOI]
- L. Gong, "Recognition of disease genetic information from unstructured text data based on bilstm-crf for molecular mechanisms", Security and Communication Networks, 2021 (2021)[DOI]
- M. A. Bou-Rabee, "BiLSTM network-based approach for solar irradiance forecasting in continental climate zones", Energies, 15(6) (2022)[DOI]
- Y. Zhan, "Combined remaining life prediction of multiple bearings based on EEMD-BILSTM", Symmetry, 14(2) (2022)[DOI]
- Y. L. Miao, "Aspect-based sentiment analysis in Chinese based on mobile reviews for BiLSTM-CRF", Journal of Intelligent & Fuzzy Systems, 40(5), pp.8697~8707 (2021)[DOI]
- "LSTM: a search space odyssey" (2017)[URL]
- D. Ma, "Short-term subway passenger flow prediction based on GCN-BiLSTM", IOP Conference Series: Earth and Environmental Science, 693(1) (2021)
- S. Choudhary, "Analysis of KDD-Cup’99, NSL-KDD and UNSW-NB15 datasets using deep learning in IoT", Procedia Computer Science, 167, pp.1561~1573 (2020)[DOI]
- V. Kanimozhi, "Artificial intelligence based network intrusion detection with hyperparameter optimization tuning on the realistic cyber dataset CSE-CIC-IDS2018 using cloud computing", ICT Express, 5(3), pp.211~214 (2019)[DOI]