Network Intrusion Detection Based on Deep Neural Network and Federated Learning

doi:10.19678/j.issn.1000-3428.0065155

Abstract

Abstract: In a high-speed network environment, complex and diverse network intrusions must be detected rapidly and accurately.As a new technology, federated learning has successfully reduced intrusion detection time and improved data security.Meanwhile, Deep Neural Network(DNN) exhibits high parallel computing ability in managing massive data.A network intrusion detection model that combines the federated learning framework with a DNN based on automatic encoder optimization as a general model, abbreviated as DFC-NID, is established.The initial data are preprocessed using symbol data and normalized, and the feature dimension of the DNN is reduced using automatic encoder technology to obtain the module for the DNN general model. Federated learning enables multiple participants to participate in training using the general model.After training is completed, the parameters are uploaded to a central server and the general model is updated repeatedly.The final classification prediction results are obtained using the Softmax classifier.Experimental results show that the accuracy of the DFC-NID model on NSL-KDD and KDDCup99 datasets is 94.1% on average, which is 3.1% higher than that of typical intrusion detection models such as decision tree and random forest.The accuracy of the DFC-NID model on attack DoS and Probe is 99.8% and 98.7%, respectively.In addition, compared with a NO-FC model without federated learning, the DFC-NID reduces the training time by 83.9%.

Key words: network intrusion detection, Deep Neural Network(DNN), federated learning, machine learning, deep learning

摘要： 在高速网络环境中，对复杂多样的网络入侵进行快速准确的检测成为目前亟待解决的问题。联邦学习作为一种新兴技术，在缩短入侵检测时间与提高数据安全性上取得了很好的效果，同时深度神经网络（DNN）在处理海量数据时具有较好的并行计算能力。结合联邦学习框架并将基于自动编码器优化的DNN作为通用模型，建立一种网络入侵检测模型DFC-NID。对初始数据进行符号数据预处理与归一化处理，使用自动编码器技术对DNN实现特征降维，以得到DNN通用模型模块。利用联邦学习特性使得多个参与方使用通用模型参与训练，训练完成后将参数上传至中心服务器并不断迭代更新通用模型，通过Softmax分类器得到最终的分类预测结果。实验结果表明，DFC-NID模型在NSL-KDD与KDDCup99数据集上的准确率平均达到94.1%，与决策树、随机森林等常用入侵检测模型相比，准确率平均提升3.1%，在攻击类DoS与Probe上，DFC-NID的准确率分别达到99.8%与98.7%。此外，相较不使用联邦学习的NO-FC模型，DFC-NID减少了83.9%的训练时间。

关键词: 网络入侵检测, 深度神经网络, 联邦学习, 机器学习, 深度学习

CLC Number:

TP309

LIU Jinshuo, ZHAN Daiyi, DENG Juan, WANG Lina. Network Intrusion Detection Based on Deep Neural Network and Federated Learning[J]. Computer Engineering, 2023, 49(1): 15-21,30.

刘金硕, 詹岱依, 邓娟, 王丽娜. 基于深度神经网络和联邦学习的网络入侵检测[J]. 计算机工程, 2023, 49(1): 15-21,30.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0065155

http://www.ecice06.com/EN/Y2023/V49/I1/15

Figures/Tables 14

References

[1] AYO F E, FOLORUNSO S O, ABAYOMI-ALLI A A, et al.Network intrusion detection based on deep learning model optimized with rule-based hybrid feature selection[J].Information Security Journal:A Global Perspective, 2020, 29(6):267-283.
[2] MA Z, LI J, SONG Y, et al.Network intrusion detection method based on FCWGAN and BiLSTM[J].Computa-tional Intelligence and Neuroscience, 2022, 15:6591140.
[3] LI Z P, QIN Z, HUANG K, et al.Intrusion detection using convolutional neural networks for representation learning[C]//Proceedings of International Conference on Neural Information Processing.Berlin, Germany:Springer, 2017:858-866.
[4] ZARAI R, KACHOUT M, HAZBER M A G, et al.Recurrent neural networks and deep neural networks based on intrusion detection system[J].OALib, 2020, 7(3):1-11.
[5] SUWANNALAI E, POLPRASERT C.Network intrusion detection systems using adversarial reinforcement learning with deep Q-network[C]//Proceedings of the 18th International Conference on ICT and Knowledge Engineering.Washington D.C., USA:IEEE Press, 2020:1-7.
[6] ZHAO R J, LI Z J, XUE Z, et al.A novel approach based on lightweight deep neural network for network intrusion detection[C]//Proceedings of IEEE Wireless Communications and Networking Conference.Washington D.C., USA:IEEE Press, 2021:1-6.
[7] CANER S, ERDOĞMUŞ N, ERTEN Y M.Performance analysis and feature selection for network-based intrusion detection with deep learning[J].Turkish Journal of Electrical Engineering and Computer Sciences, 2022, 30(3):629-643.
[8] 生龙, 袁丽娜, 武南南, 等.基于GSA与DE优化混合核ELM的网络异常检测模型[J].计算机工程, 2022, 48(6):146-153. SHENG L, YUAN L N, WU N N, et al.Network anomaly detection model based on GSA and DE optimizing hybrid kernel ELM[J].Computer Engineering, 2022, 48(6):146-153.(in Chinese)
[9] AL-SAREM M, SAEED F, ALKHAMMASH E H, et al.An aggregated mutual information based feature selection with machine learning methods for enhancing IoT botnet attack detection[J].Sensors, 2021, 22(1):185.
[10] WANG Z H, LIU J H, SUN L Y.EFS-DNN:an ensemble feature selection-based deep learning approach to network intrusion detection system[J].Security and Communication Networks, 2022, 10:1-14.
[11] CHAUHAN P S, KSHETRI N.2021 state of the practice in data privacy and security[J].Computer, 2021, 54(8):125-132.
[12] ANDRADE M L, ALCÂNTARA S M, COTA D F H.Reconfigurable FPGA-based K-means/K-modes architecture for network intrusion detection[J].IEEE Transactions on Circuits and Systems II:Express Briefs, 2020, 67(8):1459-1463.
[13] YIN X F, ZHU Y M, HU J K.A comprehensive survey of privacy-preserving federated learning:a taxonomy, review, and future directions[J].ACM Computing Surveys, 2022, 54(6):131.
[14] FRIHA O, FERRAG M A, SHU L, et al.FELIDS:federated learning-based intrusion detection system for agricultural Internet of Things[J].Journal of Parallel and Distributed Computing, 2022, 165:17-31.
[15] CIREGAN D, MEIER U, SCHMIDHUBER J.Multi-column deep neural networks for image classification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2012:3642-3649.
[16] GUO J, WANG L.Learning to upgrade Internet information security and protection strategy in big data era[J].Computer Communications, 2020, 160:150-157.
[17] 王旭仁, 马慧珍, 冯安然, 等.基于信息增益与主成分分析的网络入侵检测方法[J].计算机工程, 2019, 45(6):175-180. WANG X R, MA H Z, FENG A R, et al.Network intrusion detection method based on information gain and principal components analysis[J].Computer Engineering, 2019, 45(6):175-180.(in Chinese)
[18] CHOWDHURY R, SEN S, ROY A, et al.An optimal feature based network intrusion detection system using bagging ensemble method for real-time traffic analysis[J].Multimedia Tools and Applications, 2022, 81(28):41225-41247.
[19] GHOSH P, ALAM Z, SHARMA R R, et al.An efficient SGM based IDS in cloud environment[J].Computing, 2022, 104(3):553-576.
[20] BEULAH J R, NALINI M, IRENE D S, et al.Enhancing detection of R2L attacks by multistage clustering based outlier detection[J].Wireless Personal Communications, 2022, 124(3):2637-2659.
[21] TAVALLAEE M, BAGHERI E, LU W, et al.A detailed analysis of the KDDCup99 data set[C]//Proceedings of IEEE Symposium on Computational Intelligence for Security and Defense Applications.Washington D.C., USA:IEEE Press, 2009:1-6.
[22] GOWDHAMAN V, DHANAPAL R.An intrusion detection system for wireless sensor networks using deep neural network[J].Soft Computing, 2022, 26(23):13059-13067.
[23] HUSSAIN G K J, MANOJ G.Federated learning:a survey of a new approach to machine learning[C]//Proceedings of the 1st International Conference on Electrical, Electronics, Information and Communication Technologies.Washington D.C., USA:IEEE Press, 2022:1-8.
[24] TRELEAVEN P, SMIETANKA M, PITHADIA H.Federated learning:the pioneering distributed machine learning and privacy-preserving data technology[J].Computer, 2022, 55(4):20-29.
[25] PANDA S K, BHOI S K, SINGH M.A collaborative filtering recommendation algorithm based on normalization approach[J].Journal of Ambient Intelligence and Humanized Computing, 2020, 11(11):4643-4665.
[26] PATEL O P, TIWARI A, BAGADE V.Quantum-inspired stacked auto-encoder-based deep neural network algorithm (Q-DNN)[J].Arabian Journal for Science and Engineering, 2018, 43(12):6929-6943.
[27] RASHIDI B, ZHAO Q.Output-related fault detection in non-stationary processes using constructive correlative-SAE and demoting correlative-DNN[J].Applied Soft Computing, 2022, 123:108898.
[28] RAVI V, CHAGANTI R, ALAZAB M.Recurrent deep learning-based feature fusion ensemble meta-classifier approach for intelligent network intrusion detection system[J].Computers and Electrical Engineering, 2022, 102:108156.
[29] KONIKI R, AMPAPURAPU M D, KOLLU P K.An anomaly based network intrusion detection system using LSTM and GRU[C]//Proceedings of International Conference on Electronic Systems and Intelligent Computing.Washington D.C., USA:IEEE Press, 2022:79-84.
[30] SAMRIYA J K, TIWARI R, CHENG X, et al.Network intrusion detection using ACO-DNN model with DVFS based energy optimization in cloud framework[J].Sustainable Computing:Informatics and Systems, 2022, 35:100746.

Please choose a citation manager

Content to export