计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230300142-8.doi: 10.11896/jsjkx.230300142
白万荣1, 魏峰1, 郑广远2, 王宝会2
BAI Wanrong1, WEI Feng1, ZHENG Guangyuan2, WANG Baohui2
摘要： 网络安全直接关系到国家安全,如何准确高效地检测到电网中的网络威胁至关重要。针对传统CNN感受野较小以及未考虑数据时序特征的问题,结合网络流量数据的空间特征和时间特征,提出了一种基于时间卷积网络(TCN)和双向长短期记忆网络(BiLSTM)的注意力入侵检测算法。首先将网络流量特征进行特征编码,再使用森林优化特征筛选算法,减少数据的冗余性;然后进行重采样,解决数据不平衡问题;最后将数据输入到深度神经网络中,处理后的数据经过TCN和BiLSTM网络进行特征学习,通过自注意力机制进行权重分配,最终进行分类,实现入侵检测。在NSL-KDD数据集上进行对比实验,相比CNN-BiLSTM注意力模型,所提方法的准确率提升4.3%,F1值提升1.8%,实验结果表明,该算法能有效地对网络入侵检测进行识别。
中图分类号:
| [1]NIKOLOVA E,JECHEVA V.Some similarity coefficients andapplication of data mining techniques to the anomalybased IDS[J].Telecommunication Systems,2012,50(2):127-135. [2]ALAZAB A,ABAWAJY J,HOBBS M,et al.Crime toolkits:the productisation of cybercrime[C]// IEEE.IEEE,2013:1626-1632. [3]XIAO L,CHEN Y,CHANG C K.Bayesian Model Averaging of Bayesian Network Classifiers for Intrusion Detection[C]//Computer Software & Applications Conference Workshops.IEEE,2014. [4]JING X Y,BI Y,DENG H.An innovative two-stage fuzzykNN-DST classifier for unknown intrusion detection[J].International Arab Journal of Information Technology,2016,13(4):359-366. [5]OHKI T,GUPTA V,NISHIGAKI M.Efficient Spoofing Attack Detection against Unknown Sample using End-to-End Anomaly Detection[C]//Asia-Pacific Signal and Information Processing Association Annual Summit and Conference(APSIPA ASC).2019. [6]ALSAADI H I,ALMUTTAIRIR M,BAYAT O,et al.Computational Intelligence Algorithms to Handle Dimensionality Reduction for Enhancing Intrusion Detection System [J].Journal of Information Science andEngineering 2020,36:293-308. [7]TANG C F,BULI N,AI Z.Research on networkintrusion detection based on LightGBM[J].Computer Applications and Software,2022,39(8):298-311. [8]YU Y,LIU G,YAN H,et al.Attention-based BiLSTM modelfor anoma- lous HTTP traffic detection[C]//15th International Conference on Service Systems and Service Management.2018:1-6. [9]TAN M,IACOVAZZI A,CHEUNG N M M,et al.A neural attention model for real-time network intrusion detection[C]//2019 IEEE 44th Conference on Local Computer Networks.2019:291-299. [10]AHSAN M,NYGARD K E.Convolutional neural networkswith LSTM for intrusion detection[C]// Proceeding of 35th International Conference on Computers and Their Applications.2020:69-79. [11]GURUNG S,GHOSE M K,SUBEDI A.Deep learning approach on network intrusion detection system using NSL-KDD dataset[J].International Journal of Computer Network and Information Security,2019,11(3):8-14. [12]HSU C M,HSIEH H Y,PRAKOSA S W,et al.Using longshort term memory based convolutional neural networks for network intrusion detection[C]//International Wireless Internet Conference.2018:86-94. [13]GHAEMI M,FEIZI-DERAKHSHI M R.Forest optimization algorithm[J].Expert Systems with Applications,2014,41(15):6676-6687. [14]CHU B,LI Z S,ZHANG M L,et al.Research onImprovements ofFeature Selection Using Forest Optimization Algorithm[J].Journal of Software,2018,29(9):2545-2558. [15]BAI S,KOLTER J Z,KOLTUN V.An empirical evaluation of generic convolutionalandrecurrent networks for sequence mode-ling[J].arXiv:1803.01271,2018. |
|
||
首页