USING REAL-TIME NEURAL NETWORKS IN INTRUSION DETECTION SYSTEMS
DOI:
https://doi.org/10.34185/1991-7848.itmm.2025.01.096Keywords:
neural networks, online learning, NIDS, intrusion detection, incremental learning, cybersecurity, Extreme Learning Machine, T-DFNN.Abstract
This paper addresses the pressing limitations of modern intrusion detection systems (NIDS), which are typically based on predefined text-based rules. Such an approach hinders the detection of new or modified attacks, as these static rules can easily be evaded by attackers using minimal modifications. As a promising direction, the study explores the implementation of neural networks equipped with online learning capabilities. Several state-of-the-art solutions are analyzed, including Online Sequential Extreme Learning Machine (OS-ELM), T-DFNN, and various incremental deep neural network models, all of which demonstrate the ability to adapt in real time. The work not only summarizes current methodologies but also emphasizes the significant potential of online learning to enhance the effectiveness and flexibility of cybersecurity systems, particularly in the dynamic detection of emerging network threats.
References
Sagar N. Shah, Ms. Purnima Singh. Signature-Based Network Intrusion Detection System Using SNORT And WINPCAP. INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT). 2012. T. 01, № 10.
Kothamali, P. Reddy & Banik, S. Limitations of Signature-Based Threat Detection. 2022.
Detecting Zero-days with SnortML White Paper. Cisco. URL: https://www.cisco.com/c/en/us/products/collateral/security/firewalls/detecting-zero-days-with-snortml-wp.html (date of access: 13.04.2025).
Li Y., Qiu R., Jing S. Intrusion detection system using Online Sequence Extreme Learning Machine (OS-ELM) in advanced metering infrastructure of smart grid. PLOS ONE. 2018. Vol. 13, no. 2. P. e0192216. URL: https://doi.org/10.1371/journal.pone.0192216 (date of access: 13.04.2025).
Data M., Aritsugi M. T-DFNN: An Incremental Learning Algorithm for Intrusion Detection Systems. IEEE Access. 2021. Vol. 9. P. 154156–154171. URL: https://doi.org/10.1109/access.2021.3127985 (date of access: 13.04.2025).
Intrusion Detection System Based on Deep Neural Network and Incremental Learning for In-Vehicle CAN Networks / J. Lin et al. Communications in Computer and Information Science. Singapore, 2022. P. 255–267. URL: https://doi.org/10.1007/978-981-19-0468-4_19 (date of access: 13.04.2025).
Malialis K., Panayiotou C. G., Polycarpou M. M. Nonstationary Data Stream Classification with Online Active Learning and Siamese Neural Networks. Neurocomputing. 2022. URL: https://doi.org/10.1016/j.neucom.2022.09.065 (date of access: 13.04.2025).
