Deep logarithmic neural network for Internet intrusion detection

被引:15
作者
Wang, Zhendong [1 ]
Xu, Zhenyu [1 ]
He, Daojing [2 ]
Chan, Sammy [3 ]
机构
[1] Jiangxi Univ Sci & Technol, Sch Informat Engn, Ganzhou, Jiangxi, Peoples R China
[2] East China Normal Univ, Sch Software Engn, Shanghai, Peoples R China
[3] City Univ Hong Kong, Dept Elect Engn, Hong Kong, Peoples R China
基金
美国国家科学基金会;
关键词
Intrusion detection; Deep learning; Logarithmic neuron; Logarithmic neural network; Logarithmic neural network layer; Loss function of anti-gradient vanishing; DETECTION SYSTEM; GENETIC ALGORITHM; MACHINE; MODEL;
D O I
10.1007/s00500-021-05987-9
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Intrusion detection is an important means to deal with network attacks. The traditional neural network needs to preprocess the sample data in intrusion detection, which may cause the loss in data accuracy, thus affecting the performance of intrusion detection. In this paper, a logarithm neuron (LOGN) is designed, and each LOGN is responsible for processing a kind of data feature. Different from the traditional neuron operation rules, the logarithm operation is carried out in the LOGN, and the base number of logarithm operations in each LOGN can be determined by the neural network according to the actual task requirements. Because the increase and decrease of logarithm operation are different under different logarithmic base values, the sensitivity of LOGN to the change of sample data feature values is also different, which makes LOGN have higher capability in data feature extraction. Based on LOGN, the logarithmic neural network layer (LOGL) is designed. Logarithmic neural network (LOGNN) is constructed by combining LOGLs with traditional deep neural network. To prevent the gradient of LOGNN from disappearing, a loss function of anti-gradient vanishing (AGLF) is proposed. Experimental results show that LOGNN has obvious advantages over traditional machine learning and deep neural network methods in terms of performance indices on NSL_ KDD and UNSW_ NB_15 data sets.
引用
收藏
页码:10129 / 10152
页数:24
相关论文
共 45 条
[1]   Numerical investigations of a new singular second-order nonlinear coupled functional Lane-Emden model [J].
Abdelkawy, Mohamed A. ;
Sabir, Zulqurnain ;
Guirao, Juan L. G. ;
Saeed, Tareq .
OPEN PHYSICS, 2020, 18 (01) :770-778
[2]   Binary Multi-Objective Grey Wolf Optimizer for Feature Selection in Classification [J].
Al-Tashi, Qasem ;
Abdulkadir, Said Jadid ;
Rais, Helmi Md ;
Mirjalili, Seyedali ;
Alhussian, Hitham ;
Ragab, Mohammed G. ;
Alqushaibi, Alawi .
IEEE ACCESS, 2020, 8 :106247-106263
[3]   LR-HIDS: logistic regression host-based intrusion detection system for cloud environments [J].
Besharati, Elham ;
Naderan, Marjan ;
Namjoo, Ehsan .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2019, 10 (09) :3669-3692
[4]   A Hybrid Feature Selection Method for Improved Detection of Wired/Wireless Network Intrusions [J].
Beulah, J. Rene ;
Punithavathani, D. Shalini .
WIRELESS PERSONAL COMMUNICATIONS, 2018, 98 (02) :1853-1869
[5]  
Briongos S., 2019, ANOMALY DETECTION US, DOI [10.1007/978-3-030-29859-3_55, DOI 10.1007/978-3-030-29859-3_55]
[6]  
Canêdo D, 2019, IEEE LAT AM T, V17, P1109, DOI 10.1109/TLA.2019.8931198
[7]   Network traffic classification using deep convolutional recurrent autoencoder neural networks for spatial-temporal features extraction [J].
D'Angelo, Gianni ;
Palmieri, Francesco .
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2021, 173
[8]   GGA: A modified genetic algorithm with gradient-based local search for solving constrained optimization problems [J].
D'Angelo, Gianni ;
Palmieri, Francesco .
INFORMATION SCIENCES, 2021, 547 :136-162
[9]  
De-Yi, 2018, CH J COMPUT, V41, P1619
[10]   Machine Learning in Medicine [J].
Deo, Rahul C. .
CIRCULATION, 2015, 132 (20) :1920-1930