Multi-Stage Optimized Machine Learning Framework for Network Intrusion Detection

被引:138
作者
Injadat, Mohammad Noor [1 ]
Moubayed, Abdallah [1 ]
Nassif, Ali Bou [1 ,2 ]
Shami, Abdallah [1 ]
机构
[1] Univ Western Ontario, Dept Elect & Comp Engn, London, ON N6A 5B9, Canada
[2] Univ Sharjah, Dept Comp Engn, Sharjah, U Arab Emirates
来源
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT | 2021年 / 18卷 / 02期
关键词
Feature extraction; Intrusion detection; Training; Optimization; Correlation; Machine learning; Organizations; Network intrusion detection; machine learning; hyper-parameter optimization; Bayesian optimization; particle swarm optimization; genetic algorithm; PARTICLE SWARM OPTIMIZATION; DETECTION SYSTEM; GENETIC ALGORITHM; FEATURE-SELECTION; RANDOM-FORESTS; MODEL; SMOTE;
D O I
10.1109/TNSM.2020.3014929
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Cyber-security garnered significant attention due to the increased dependency of individuals and organizations on the Internet and their concern about the security and privacy of their online activities. Several previous machine learning (ML)-based network intrusion detection systems (NIDSs) have been developed to protect against malicious online behavior. This paper proposes a novel multi-stage optimized ML-based NIDS framework that reduces computational complexity while maintaining its detection performance. This work studies the impact of oversampling techniques on the models' training sample size and determines the minimal suitable training sample size. Furthermore, it compares between two feature selection techniques, information gain and correlation-based, and explores their effect on detection performance and time complexity. Moreover, different ML hyper-parameter optimization techniques are investigated to enhance the NIDS's performance. The performance of the proposed framework is evaluated using two recent intrusion detection datasets, the CICIDS 2017 and the UNSW-NB 2015 datasets. Experimental results show that the proposed model significantly reduces the required training sample size (up to 74%) and feature set size (up to 50%). Moreover, the model performance is enhanced with hyper-parameter optimization with detection accuracies over 99% for both datasets, outperforming recent literature works by 1-2% higher accuracy and 1-2% lower false alarm rate.
引用
收藏
页码:1803 / 1816
页数:14
相关论文
共 75 条
[1]   BotChase: Graph-Based Bot Detection Using Machine Learning [J].
Abou Daya, Abbas ;
Salahuddin, Mohammad A. ;
Limam, Noura ;
Boutaba, Raouf .
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2020, 17 (01) :15-29
[2]   A hybrid genetic algorithm for optimization of scheduling workflow applications in heterogeneous computing systems [J].
Ahmad, Saima Gulzar ;
Liew, Chee Sun ;
Munir, Ehsan Ullah ;
Fong, Ang Tan ;
Khan, Samee U. .
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2016, 87 :80-90
[3]   Intelligent intrusion detection in external communication systems for autonomous vehicles [J].
Alheeti, Khattab M. Ali ;
McDonald-Maier, Klaus .
SYSTEMS SCIENCE & CONTROL ENGINEERING, 2018, 6 (01) :48-56
[4]   Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model [J].
Aljawarneh, Shadi ;
Aldwairi, Monther ;
Yassein, Muneer Bani .
JOURNAL OF COMPUTATIONAL SCIENCE, 2018, 25 :152-160
[5]   DDoS Detection System: Using a Set of Classification Algorithms Controlled by Fuzzy Logic System in Apache Spark [J].
Alsirhani, Amjad ;
Sampalli, Srinivas ;
Bodorik, Peter .
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2019, 16 (03) :936-949
[6]  
[Anonymous], 2007, NIPS
[7]  
Ashlock D., 2006, EVOLUTIONARY COMPUTA
[8]   A New Intrusion Detection Approach using PSO based Multiple Criteria Linear Programming [J].
Bamakan, Seyed Mojtaba Hosseini ;
Amiri, Behnam ;
Mirzabagheri, Mahboubeh ;
Shi, Yong .
3RD INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND QUANTITATIVE MANAGEMENT, ITQM 2015, 2015, 55 :231-237
[9]  
Ben Salem M, 2008, ADV INFORM SECUR, V39, P69
[10]  
Bergstra J, 2012, J MACH LEARN RES, V13, P281