2023
DOI: 10.3390/s23031315
|View full text |Cite
|
Sign up to set email alerts
|

Development of a Machine-Learning Intrusion Detection System and Testing of Its Performance Using a Generative Adversarial Network

Abstract: Intrusion detection and prevention are two of the most important issues to solve in network security infrastructure. Intrusion detection systems (IDSs) protect networks by using patterns to detect malicious traffic. As attackers have tried to dissimulate traffic in order to evade the rules applied, several machine learning-based IDSs have been developed. In this study, we focused on one such model involving several algorithms and used the NSL-KDD dataset as a benchmark to train and evaluate its performance. We… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 13 publications
(5 citation statements)
references
References 21 publications
0
2
0
Order By: Relevance
“…In 2023, A. Mari et al. [13] suggest using GANs in IDS to enhance attack detection performance which is applied on the NSL‐KDD dataset. In this research, GANs are applied to synthesis instances which leads to enhance attack detection using ML classifiers.…”
Section: Related Workmentioning
confidence: 99%
“…In 2023, A. Mari et al. [13] suggest using GANs in IDS to enhance attack detection performance which is applied on the NSL‐KDD dataset. In this research, GANs are applied to synthesis instances which leads to enhance attack detection using ML classifiers.…”
Section: Related Workmentioning
confidence: 99%
“…GANs were also applied for detecting adversarial attacks, significantly improving AIDS performance. In 2023, the authors in [8] suggested using GANs in IDS to enhance attack detection on the NSL-KDD dataset. GANs were applied to synthesize instances, improving attack detection with ML classifiers, including KNN, Decision Tree (DT), RF, SVM, and ANN.…”
Section: Related Workmentioning
confidence: 99%
“…The discriminator is similar to the ordinary binary classification network. It accepts the data set of the input sample x, including the samples sampled from the real data distribution, and also includes the false samples sampled from the generated network, which together form the discriminator training data set [25]. The discriminator output is the probability P belonging to the real sample, the labels of all real samples are labeled as true, and the samples generated by all generators are labeled as false.…”
Section: Discriminatormentioning
confidence: 99%