Using Machine Learning to Analyze Network Traffic Anomalies

被引:1
作者
Khudoyarova, Anastasia [1 ]
Burlakov, Mikhail [1 ]
Kupriyashin, Mikhail [1 ]
机构
[1] Natl Res Nucl Univ MEPhI, Moscow Engn Phys Inst, Moscow, Russia
来源
PROCEEDINGS OF THE 2021 IEEE CONFERENCE OF RUSSIAN YOUNG RESEARCHERS IN ELECTRICAL AND ELECTRONIC ENGINEERING (ELCONRUS) | 2021年
关键词
network traffic anomaly; machine learning; traffic analysis; intrusion detection; Kalman filter; Bayesian networks;
D O I
10.1109/ElConRus51938.2021.9396246
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, we study the application of machine learning methods, as well as spectral and statistical methods for real time network traffic anomaly detection. We determine the strengths and weaknesses of the existing methods and compare them in terms of efficiency. We then build a system of criteria to ensure the most efficient anomaly detection while meeting the specified system performance and resource consumption requirements. As a result, we suggest a set of the most effective anomaly detection methods as well as recommendations on the underlying system architecture.
引用
收藏
页码:2344 / 2348
页数:5
相关论文
共 16 条
[1]   Anomaly detection in communication networks using wavelets [J].
Alarcon-Aquino, V ;
Barria, JA .
IEE PROCEEDINGS-COMMUNICATIONS, 2001, 148 (06) :355-362
[2]  
[Anonymous], 2003, BAYESIAN FILTERING K
[3]  
Bivens A., 2002, P INT ENG SYST NEUR, V12, P579
[4]  
Cannady J., 1998, Proc. Nat. Inf. Syst. Secur. Conf, P443
[5]  
Dehghannasiri R., 2016, P AS C SIGN SYST COM
[6]   Architecture for an Artificial Immune System [J].
Hofmeyr, Steven A. ;
Forrest, Stephanie .
EVOLUTIONARY COMPUTATION, 2000, 8 (04) :443-473
[7]   Mining anomalies using traffic feature distributions [J].
Lakhina, A ;
Crovella, M ;
Diot, C .
ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2005, 35 (04) :217-228
[8]  
Lakhina A., 2004, Performance Evaluation Review, V32, P61, DOI 10.1145/1012888.1005697
[9]  
Lindingrin A.N., 2019, IZVESTIA TULSKOGO GO
[10]  
Shelukhin O. I., 2013, T COMM TELECOMMUNICA, V7, P28