Abstract
With the rapid development of Internet technology, network attacks occur frequently and numerous hidden dangers appear in network security. Therefore, improving the performance of intrusion detection systems to detect and defend against attacks is the key to ensuring network security. However, in the face of complex and massive network data feature information, traditional machine learning methods suffer from data imbalance and feature redundancy, which results in low detection rates, high false alarm rates and poor real-time performance of intrusion detection systems. Therefore, to address these problems, this paper proposes a data imbalance-based Convolutional Neural Network Intrusion Detection Method (CNN-IDMDI). First, an oversampling method is used to solve the data imbalance problem by decomposing the increased number of samples for the few attacks with multiple sampling to form multiple sub-samples. Second, the gradient coordination mechanism and the improved loss function Focal Loss are combined to calculate the loss between the actual and expected values to detect network malicious attacks in high-dimensional and unbalanced data. Finally, the methods in this paper are compared with the current mainstream intrusion detection methods on the NSL-KDD dataset for binary and multi-classification detection. The experimental results show that the method in this paper can effectively improve the effectiveness of CNN intrusion detection and network anomaly. The average accuracy of the CNN intrusion detection method based on data imbalance for binary intrusion detection is 98.73% and the implementation time of the method is 1.42 s, which is 15.45%, 12.76%, and 2.91% higher than the average accuracy of the CNN, the CNN Long Short-Term Memory (CNN-LSTM) and the CNN Neural-induced Support Vector Machine (CNN-NSVM) methods, respectively, and the detection time is saved by 0.82 s, 0.72 s, and 0.61 s, respectively. The average accuracy of the CNN intrusion detection method based on data imbalance for multi-classification intrusion detection is 94.55% and the time required to complete the detection is 2.96 s. This improves the average accuracy by 16.09%, 12.71%, and 3.66% compared with the CNN, CNN-LSTM and CNN-NSVM methods, respectively. It is also quicker, as the time consumption of CNN is 8.84 s, CNN-LSTM is 8.31 s and CNN-NSVM is 6.43 s. Therefore, the CNN-IDMDI method for intrusion detection proposed in this paper has higher accuracy and faster speed.
Similar content being viewed by others
Data availability
A significant amount of data is presented in this article. The remaining data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions.
References
Xia LM, Li ZM (2021) A new method of abnormal behavior detection using LSTM network with temporal attention mechanism. J Supercomput 77(4):773223–773241. https://doi.org/10.1007/s11227-020-03391-y
Zhu YK, Gaba GS, Almansour FM, Alroobaea R, Masud M (2021) Application of data mining technology in detecting network intrusion and security maintenance. J Intell Syst 30(1):664–676. https://doi.org/10.1515/jisys-2020-0146
Lu HM, Wang T, Xu X, Wang T (2022) Cognitive memory-guided autoencoder for effective intrusion detection in internet of things. IEEE Trans Industr Inf 18(5):3358–3366. https://doi.org/10.1109/TII.2021.3102637
Ramalingam GP, Annie RAX, Gopalakrishnan S (2022) Optimized fuzzy enabled semi-supervised intrusion detection system for attack prediction. Intell Autom Soft Comput 32(3):1479–1492. https://doi.org/10.32604/iasc.2022.022211
Guo YQ, Wang X (2021) Applying TS-DBN model into sports behavior recognition with deep learning approach. J Supercomput 77(10):12192–12208. https://doi.org/10.1007/s11227-021-03772-x
Czaplewski B, Zwonkowski MD (2022) A novel approach exploiting properties of convolutional neural networks for vessel movement anomaly detection and classification. ISA Trans 119:1–16. https://doi.org/10.1016/j.isatra.2021.02.030
Abbas S, Alhwaiti Y, Fatima A, Khan MA (2022) Convolutional neural network based intelligent handwritten document recognition. CMC-Comput Mater Contin 70(3):4563–4581. https://doi.org/10.32604/cmc.2022.021102
Dong YN, Liu QW, Du B, Zhang LP (2022) Weighted feature fusion of convolutional neural network and graph attention network for hyperspectral image classification. IEEE Trans Image Process 31:1559–1572. https://doi.org/10.1109/TIP.2022.3144017
Liu GJ, Zhang JB (2020) CNID: research of network intrusion detection based on convolutional neural network. Discret Dyn Nat Soc. https://doi.org/10.1155/2020/4705982
Yang J, Sheng YQ, Wang JL (2020) A GBDT-paralleled quadratic ensemble learning for intrusion detection system. IEEE Access 8:175467–175482. https://doi.org/10.1109/ACCESS.2020.3026044
Wang H, Cao ZJ, Hong B (2020) A network intrusion detection system based on convolutional neural network. J Int Fuzzy Syst 38(6):7623–7637. https://doi.org/10.3233/JIFS-179833
Lopez-Martin M, Sanchez-Esguevillas A, Arribas JI (2022) Supervised contrastive learning over prototype-label embeddings for network intrusion detection. Inform Fus 79:200–228. https://doi.org/10.1016/j.inffus.2021.09.014
Alsaleh A, Binsaeedan W (2021) The influence of salp swarm algorithm-based feature selection on network anomaly intrusion detection. IEEE Access 9:112466–112477. https://doi.org/10.1109/ACCESS.2021.3102095
Tang ZY, Hu HY, Xu CH (2021) A federated learning method for network intrusion detection. Concurr Comput-Pract Exp. https://doi.org/10.1002/cpe.6812
Liu J, Zhao HB (2021) Application of convolution neural network in medical image processing. Technol Health Care 29(2):407–417. https://doi.org/10.3233/THC-202657
Ortac G, Ozcan G (2021) Comparative study of hyperspectral image classification by multidimensional convolutional neural network approaches to improve accuracy. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2021.115280
Zhang CY, Ren J, Liu FC, Li XQ (2022) Three-way selection random forest algorithm based on decision boundary entropy. Appl Intell. https://doi.org/10.1007/s10489-021-03033-7
Lu JZ, Liu XL, Zhang SB, Chang Y (2020) Research and analysis of electromagnetic Trojan detection based on deep learning. Secur Commun Netw. https://doi.org/10.1155/2020/6641844
Mao BF, Liu J, Lai YX, Sun MT (2021) MIF: a multi-step attack scenario reconstruction and attack chains extraction method based on multi-information fusion. Comput Netw. https://doi.org/10.1016/j.comnet.2021.108340
Yu YW, Bian NZ (2020) An intrusion detection method using few-shot learning. IEEE Access 8:49730–49740. https://doi.org/10.1109/ACCESS.2020.2980136
Liang XW, Jiang AP, Li T, Xue YY, Wang GT (2020) LR-SMOTE - An improved unbalanced data set oversampling based on K-means and SVM. Knowl-Based Syst. https://doi.org/10.1016/j.knosys.2020.105845
Wang L, Han M, Li XJ, Zhang N, Cheng HD (2021) Review of classification methods on unbalanced data sets. IEEE Access 9:64606–64628. https://doi.org/10.1109/ACCESS.2021.3074243
He Y, Leng X, Wan J (2021) Unbalanced data weighted boundary point integration undersampling method. J Xid Univ 48(4):176–183
Bendjoudi I, Vanderhaegen F, Hamad D, Dornaika F (2021) Multi-label, multi-task CNN approach for context-based emotion recognition. Inform Fus 76:422–428. https://doi.org/10.1016/j.inffus.2020.11.007
Hossain MS, Betts JM, Paplinski AP (2021) Dual focal loss to address class imbalance in semantic segmentation. Neurocomputing 462:69–87. https://doi.org/10.1016/j.neucom.2021.07.055
Wang Z, Shi PB (2021) CAPTCHA recognition method based on CNN with focal loss. Complexity. https://doi.org/10.1155/2021/6641329
Dong YF, Shen XH, Jiang Z, Wang HY (2021) Recognition of imbalanced underwater acoustic datasets with exponentially weighted cross-entropy loss. Appl Acoust. https://doi.org/10.1016/j.apacoust.2020.107740
Karabayir I, Akbilgic O, Tas N (2021) A novel learning algorithm to optimize deep neural networks: evolved gradient direction optimizer (EVGO). IEEE Trans Neural Netw Learning Syst 32(2):685–694. https://doi.org/10.1109/TNNLS.2020.2979121
Song CY, Pons A, Yen K (2021) AG-SGD: angle-based stochastic gradient descent. IEEE Access 9:23007–23024. https://doi.org/10.1109/ACCESS.2021.3055993
Cheridito P, Jentzen A, Rossmannek F (2021) Non-convergence of stochastic gradient descent in the training of deep neural networks. J Complex. https://doi.org/10.1016/j.jco.2020.101540
Shin K, Han J, Kang S (2021) MI-MOTE: Multiple imputation-based minority oversampling technique for imbalanced and incomplete data classification. Inf Sci 575:80–89. https://doi.org/10.1016/j.ins.2021.06.043
Wang JR, Li SM (2019) Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines. Neurocomputing 329:53–65. https://doi.org/10.1016/j.neucom.2018.10.049
Yu YL, Liu FX (2019) Effective neural network training with a new weighting mechanism-based optimization algorithm. IEEE Access 7:72403–72410. https://doi.org/10.1109/ACCESS.2019.2919987
Gurung S, Ghose MK, Subedi A (2019) Deep learning approach on network intrusion detection system using NSL-KDD dataset. Int J Comput Netw Inform Secur 11(3):8–14. https://doi.org/10.5815/ijcnis.2019.03.02
Li SQ, Zhang ZY, Liu Y (2020) A short-term traffic flow reliability prediction method considering traffic safety. Math Probl Eng. https://doi.org/10.1155/2020/6682216
Hosseini S (2020) A new machine learning method consisting of GA-LR and ANN for attack detection. Wireless Netw 26(6):4149–4162. https://doi.org/10.1007/s11276-020-02321-3
Wei Y, Hui C, Ze YC (2021) Tibetan text classification based on RNN. In: 4TH International Conference on Advanced Algorithms And Control Engineering (ICAACE 2021), 29-31 Jan, 2021, Sanya, China, Journal Of Physics: Conference series: 012139. https://doi.org/10.1088/1742-6596/1848/1/012139
Zhao L, Fang W (2021) An Efficient and Flexible Automatic Search Algorithm for Convolution Network Architectures. In: 2021 IEEE Congress on Evolutionary Computation (CEC 2021), Jun 28-JUL 01, 2021, KRAKÓW, Poland, IEEE Congress on Evolutionary Computation:2203–2210. https://doi.org/10.1109/CEC45853.2021.9504945
Zhao RJ, Li ZJ, Xue Z (2021) A Novel Approach based on Lightweight Deep Neural Network for Network Intrusion Detection. In: 2021 IEEE Wireless Communications And Networking Conference (WCNC), MAR 29-APR 01, 2021, Nanjing, China, IEEE Computer Society:1–6. https://doi.org/10.1109/WCNC49053.2021.9417568
Yan XG, Gao L (2020) A feature extraction and classification algorithm based on improved sparse auto-encoder for round steel surface defects. Math Biosci Eng 17(5):5369–5394. https://doi.org/10.3934/mbe.2020290
Li JM, Wu WF, Xue D (2020) Research on transfer learning algorithm based on support vector machine. J Int Fuzzy Syst 38(4):4091–4106. https://doi.org/10.3233/JIFS-190055
Xing H, Cheng L (2019) A design method for deep belief network based on reinforcement learning. Control Engineering Of China: pp 262115–2120.
Chen J, Miao YK (2021) Study on network security intrusion target detection method in big data environment. Int J Internet Protoc Technol 14(4):240–247. https://doi.org/10.1504/IJIPT.2021.118966
Wang DB, Xu GY (2020) Research on the detection of network intrusion prevention with SVM based optimization algorithm. Inform-An Int J Comput Inform 44(2):269–273. https://doi.org/10.31449/inf.v44i2.3195
Pan T, Zhao J, Wu W, Yang J (2020) Learning imbalanced datasets based on SMOTE and Gaussian distribution. Inf Sci 512:1214–1233. https://doi.org/10.1016/j.ins.2019.10.048
Suwannalai E, Polprasert C (2020) Network intrusion detection systems using adversarial reinforcement learning with deep q-network. In: 18TH International Conference On ICT And Knowledge Engineering (ICT&KE),18–20 NOV 2020, Bangkok, Thailand, IEEE Computer Society:1–7. https://doi.org/10.1109/ICTKE50349.2020.9289884
Acknowledgements
This research reports results from the scientific research project of special projects in key areas of the Guangdong Provincial Department of Education (No.2021ZDZX1104); Basic and Applied Basic Research Project of Guangzhou Basic Research Program in 2022 (No. 202201010106); Guangzhou Philosophy and Social Science Planning Project (No. 2022GZGJ241); Key scientific research projects of Guangzhou Nanyang Polytechnic (No. NY2021KYZD01); Guangdong Provincial Department of Education (No. 2020ZDZX3096); Key projects of social science and technology development in Dongguan under Grant (No. 2020507156156); Special fund for Dongguan's Rural Revitalization Strategy in 2021 (No. 20211800400102); Dongguan special commissioner project (No. 20211800500182); Dongguan Joint fund for Basic and Applied Research of Guangdong Province (No. 2020A1515110162).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare no potential conflict of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gan, B., Chen, Y., Dong, Q. et al. A convolutional neural network intrusion detection method based on data imbalance. J Supercomput 78, 19401–19434 (2022). https://doi.org/10.1007/s11227-022-04633-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-022-04633-x