Efficacy of Spiking Neural Networks for Intrusion Detection Systems

Authors

Leonard Knapp, Sven Nitzsche, Matthias Börsig, Alexandru Vasilache, Ingmar Baumgart and Juergen Becker

Abstract

Protection against potential threats is paramount in computer networks and requires robust security measures. However, traditional rule-based Intrusion Detection Systems (IDSs) often fail to adapt to dynamic environments, prompting the exploration of innovative solutions such as Neural Network (NN)-based approaches. Previous advances have primarily focused on conventional NNs. Only more recent studies researched the use of Spiking Neural Networks (SNNs) for IDSs; however, they rely on pre- or post-processing steps in their methods, which interferes with the analysis of the actual applicability of SNNs for IDSs. This study aims to overcome this deficit by analyzing the efficacy of SNNs as the sole data processor for IDSs, i.e., without using any non-essential processing outside of the network ("bare" SNNs). Through extensive experimentation on the NSL-KDD, CIC-IDS-2017, CIC-IOT-2023, and AWID3 datasets, we examined various configurations of bare SNNs, alongside conventional NNs, and Recurrent Neural Networks (RNNs) for comparison. The results demonstrate that SNNs can achieve robust performance for IDSs without the pre- or post-processing steps required by other studies. In detail, the bare SNNs achieved higher or similar accuracy for all datasets compared to the other NN models. Furthermore, a comparative analysis reveals a competitive advantage of SNNs over the other NN models in generating fewer false positives. The results of this study suggest that SNN-based IDSs are a promising direction to strengthen network security. However, further research is essential to ensure broader applicability and scalability.

Keywords

Accuracy; Recurrent neural networks; Scalability; Intrusion detection; Spiking neural networks; Network security; Performance metrics; NSL-KDD; Computer networks; Standards; Spiking neural networks; Artificial neural networks; Intrusion detection; Computer networks; Machine learning

Copyright

© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Event website: https://cyber-ai.org/2025/

Publication

2025 International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)

DOI: 10.1109/Cyber-AI66431.2025.11233776
BibTeX: Download
PDF: Download

@INPROCEEDINGS{Knapp.2025,
    author={Knapp, Leonard and Nitzsche, Sven and Börsig, Matthias and Vasilache, Alexandru and Baumgart, Ingmar and Becker, Juergen},
    title={Efficacy of Spiking Neural Networks for Intrusion Detection Systems}, 
    booktitle={2025 International Conference on Cybersecurity and AI-Based Systems (Cyber-AI)}, 
    year={2025},
    volume={},
    number={},
    pages={89-95},
    keywords={Accuracy;Recurrent neural networks;Scalability;Intrusion detection;Spiking neural networks;Network security;Performance metrics;NSL-KDD;Computer networks;Standards;Spiking neural networks;Artificial neural networks;Intrusion detection;Computer networks;Machine learning},
    doi={10.1109/Cyber-AI66431.2025.11233776},
    url={https://ieeexplore.ieee.org/document/11233776}
}