Evaluating Label Flipping Attack in Deep Learning-Based NIDS

Hesamodin Mohammadian, Arash Lashkari, Ali A. Ghorbani

2023

Abstract

Network intrusion detection systems are one of the key elements of any cybersecurity defensive system. Since these systems require processing a high volume of data, using deep learning models is a suitable approach for solving these problems. But, deep learning models are vulnerable to several attacks, including evasion attacks and poisoning attacks. The network security domain lacks the evaluation of poisoning attacks against NIDS. In this paper, we evaluate the label-flipping attack using two well-known datasets. We perform our experiments with different amounts of flipped labels from 10% to 70% of the samples in the datasets. Also, different ratios of malicious to benign samples are used in the experiments to explore the effect of datasets’ characteristics. The results show that the label-flipping attack decreases the model’s performance significantly. The accuracy for both datasets drops from 97% to 29% when 70% of the labels are flipped. Also, results show that using datasets with different ratios does not significantly affect the attack’s performance.

Paper Citation

in Harvard Style

Mohammadian H., Lashkari A. and A. Ghorbani A. (2023). Evaluating Label Flipping Attack in Deep Learning-Based NIDS. In Proceedings of the 20th International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-666-8, SciTePress, pages 597-603. DOI: 10.5220/0012038100003555

in Bibtex Style

@conference{secrypt23,
author={Hesamodin Mohammadian and Arash Lashkari and Ali A. Ghorbani},
title={Evaluating Label Flipping Attack in Deep Learning-Based NIDS},
booktitle={Proceedings of the 20th International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2023},
pages={597-603},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012038100003555},
isbn={978-989-758-666-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - Evaluating Label Flipping Attack in Deep Learning-Based NIDS
SN - 978-989-758-666-8
AU - Mohammadian H.
AU - Lashkari A.
AU - A. Ghorbani A.
PY - 2023
SP - 597
EP - 603
DO - 10.5220/0012038100003555
PB - SciTePress