Bayesian Hyperparameter Optimization for Deep Neural Network-Based Network Intrusion Detection

被引:22
|
作者
Masum, Mohammad [1 ]
Shahriar, Hossain [2 ]
Haddad, Hisham [2 ]
Faruk, Md Jobair Hossain [3 ]
Valero, Maria [2 ]
Khan, Md Abdullah [4 ]
Rahman, Mohammad A. [5 ]
Adnan, Muhaiminul, I [6 ]
Cuzzocrea, Alfredo [7 ,8 ]
Wu, Fan [9 ]
机构
[1] Kennesaw State Univ, Sch Data Sci, Kennesaw, GA 30144 USA
[2] Kennesaw State Univ, Dept Informat Technol, Kennesaw, GA 30144 USA
[3] Kennesaw State Univ, Dept Software Engn & Game Dev, Kennesaw, GA 30144 USA
[4] Kennesaw State Univ, Dept Comp Sci, Kennesaw, GA 30144 USA
[5] Florida Int Univ, Dept Elect & Comp Engn, Miami, FL 33199 USA
[6] United Int Univ, Inst Nat Sci, Washington, DC USA
[7] Univ Calabria, iDEA Lab, Arcavacata Di Rende, Italy
[8] LORIA, Nancy, France
[9] Tuskegee Univ, Dept Comp Sci, Tuskegee, AL 36088 USA
来源
2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2021年
基金
美国国家科学基金会;
关键词
Deep neural network; Network intrusion detection; Hyperparameter optimization; Bayesian optimization; Gaussian processes; Random search;
D O I
10.1109/BigData52589.2021.9671576
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditional network intrusion detection approaches encounter feasibility and sustainability issues to combat modern, sophisticated, and unpredictable security attacks. Deep neural networks (DNN) have been successfully applied for intrusion detection problems. The optimal use of DNN-based classifiers requires careful tuning of the hyper-parameters. Manually tuning the hyperparameters is tedious, time-consuming, and computationally expensive. Hence, there is a need for an automatic technique to find optimal hyperparameters for the best use of DNN in intrusion detection. This paper proposes a novel Bayesian optimization-based framework for the automatic optimization of hyperparameters, ensuring the best DNN architecture. We evaluated the performance of the proposed framework on NSL-KDD, a benchmark dataset for network intrusion detection. The experimental results show the framework's effectiveness as the resultant DNN architecture demonstrates significantly higher intrusion detection performance than the random search optimization-based approach in terms of accuracy, precision, recall, and f1-score.
引用
收藏
页码:5413 / 5419
页数:7
相关论文
共 50 条
  • [1] Network Security Enhanced with Deep Neural Network-Based Intrusion Detection System
    Alrayes, Fatma S.
    Zakariah, Mohammed
    Amin, Syed Umar
    Khan, Zafar Iqbal
    Alqurni, Jehad Saad
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 80 (01): : 1457 - 1490
  • [2] Bayesian Hyperparameter Optimization of Deep Neural Network Algorithms Based on Ant Colony Optimization
    Jlassi, Sinda
    Jdey, Imen
    Ltifi, Hela
    DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021, PT III, 2021, 12823 : 585 - 594
  • [3] Deep Neural Network-Based Intrusion Detection System through PCA
    Alotaibi, Shoayee Dlaim
    Yadav, Kusum
    Aledaily, Arwa N.
    Alkwai, Lulwah M.
    Dafhalla, Alaa Kamal Yousef
    Almansour, Shahad
    Lingamuthu, Velmurugan
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2022, 2022
  • [4] Intrusion detection system: a deep neural network-based concatenated approach
    Sharma, Hidangmayum Satyajeet
    Singh, Khundrakpam Johnson
    JOURNAL OF SUPERCOMPUTING, 2024, 80 (10): : 13918 - 13948
  • [5] Neural network-based intrusion detection systems
    Hu, LX
    He, ZJ
    COMPUTER SCIENCE AND TECHNOLOGY IN NEW CENTURY, 2001, : 296 - 298
  • [6] EXPLAINABLE DEEP NEURAL NETWORK-BASED ANALYSIS ON INTRUSION-DETECTION SYSTEMS
    Pande, Sagar Dhanraj
    Khamparia, Aditya
    COMPUTER SCIENCE-AGH, 2023, 24 (01): : 97 - 111
  • [7] Cellular Neural Network-Based Methods for Distributed Network Intrusion Detection
    Xie, Kang
    Yang, Yixian
    Xin, Yang
    Xia, Guangsheng
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2015, 2015
  • [8] Network intrusion detection algorithm based on deep neural network
    Jia, Yang
    Wang, Meng
    Wang, Yagang
    IET INFORMATION SECURITY, 2019, 13 (01) : 48 - 53
  • [9] An Improved Network Intrusion Detection Based on Deep Neural Network
    Zhang, Lin
    Li, Meng
    Wang, Xiaoming
    Huang, Yan
    2019 INTERNATIONAL CONFERENCE ON ADVANCED ELECTRONIC MATERIALS, COMPUTERS AND MATERIALS ENGINEERING (AEMCME 2019), 2019, 563
  • [10] Network-based anomaly intrusion detection improvement by Bayesian network and indirect relation
    Cha, ByungRae
    Lee, DongSeob
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS: KES 2007 - WIRN 2007, PT II, PROCEEDINGS, 2007, 4693 : 141 - 148