An Efficient Hybrid Approach for Intrusion Detection in Cyber Traffic Using Autoencoders

被引：0
作者：
Giri K. [1 ]
Gupta M. [1 ]
Dadheech P. [1 ]
机构：
[1] Department of Computer Science and Engineering, Swami Keshvanand Institute of Technology, Management and Gramothan, Jaipur
来源：
SN Computer Science | / 4卷 / 5期
关键词：
Autoencoder; Cybersecurity; Deep learning; Feature selection; Intrusion detection; Machine learning; NSL-KDD dataset; Random forest;
D O I：
10.1007/s42979-023-01865-3
中图分类号：
学科分类号：
摘要：
Intrusion detection is an essential security issue in the present digital climate. Spiteful cyber attacks can frequently hide/sneak in abundant volumes of regular data in lopsided network traffic. In cyberspace, it has a great level of stealth and opacity, making it crucial for network-based intrusion detection systems (NIDS) to assure the accuracy in detection and the given timelines. The false-positive issue is one of the inherent drawbacks of NIDS, which are widely employed to identify threats and safeguard networks. Imbalance classes and unreasonable network datasets are the main reasons behind these false positives. This paper proposes an autoencoder-based anomaly detection methodology, which uses a reconstruction error approach to generate attack samples, which are less in number in the training dataset. Feature rngineering is also performed in this paper using the recursive feature elimination method. We utilized the NSL-KDD dataset for this experiment. The result shows that our approach is better than various modern approaches in terms of various metrics such as accuracy, precision, recall, and F1 score. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
引用
收藏
相关论文
共 17 条
  • [1] Siddiqi M.A., Pak W., An agile approach to identify single and hybrid normalization for enhancing machine learning-based network intrusion detection, IEEE Access, 9, pp. 137494-137513, (2021)
  • [2] Diro A.A., Chilamkurti N., Distributed attack detection scheme using deep learning approach for Internet of Things, Future Gener Comput Syst, 82, pp. 761-768, (2018)
  • [3] Ghasemi J., Esmaily J., Moradinezhad R., Intrusion detection system using an optimized kernel extreme learning machine and efficient features, Sadhana Acad Proc Eng Sci, (2020)
  • [4] Halbouni A., Gunawan T.S., Habaebi M.H., Halbouni M., Kartiwi M., Ahmad R., Machine learning and deep learning approaches for CyberSecurity: a review, IEEE Access, 10, pp. 19572-19585, (2022)
  • [5] Al-Daweri M.S., Ariffin K.A.Z., Abdullah S., Senan M.F.E.M., An analysis of the KDD99 and UNSW-NB15 datasets for the intrusion detection system, Symmetry (Basel), 12, 10, pp. 1-32, (2020)
  • [6] Liu L., Wang P., Lin J., Liu L., Intrusion detection of imbalanced network traffic based on machine learning and deep learning, IEEE Access, 9, pp. 7550-7563, (2021)
  • [7] Chkirbene Z., Erbad A., Hamila R., Mohamed A., Guizani M., Hamdi M., TIDCS: a dynamic intrusion detection and classification system based feature selection, IEEE Access, 8, pp. 95864-95877, (2020)
  • [8] Le Jeune L., Goedeme T., Mentens N., Machine learning for misuse-based network intrusion detection: overview, unified evaluation and feature choice comparison framework, IEEE Access, 9, pp. 63995-64015, (2021)
  • [9] Akashdeep I.M., Kumar N., A feature reduced intrusion detection system using ANN classifier, Expert Syst Appl, 88, pp. 249-257, (2017)
  • [10] Jiang K., Wang W., Wang A., Wu H., Network intrusion detection combined hybrid sampling with deep hierarchical network, IEEE Access, 8, pp. 32464-32476, (2020)
12