2020
DOI: 10.1016/j.procs.2020.03.330
|View full text |Cite
|
Sign up to set email alerts
|

A Review of the Advancement in Intrusion Detection Datasets

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
110
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
6
3

Relationship

1
8

Authors

Journals

citations
Cited by 179 publications
(110 citation statements)
references
References 24 publications
0
110
0
Order By: Relevance
“…Despite not showing a significant difference between the results of the two algorithms that obtained a better performance, the authors pointed out that the classification speed was much higher after applying the PCA technique in reducing the dimensionality of the NSL-KDD dataset [9]. Thus, the need for optimizing the dataset is confirmed according to [16], [45], [52]- [54].…”
Section: Related Workmentioning
confidence: 99%
“…Despite not showing a significant difference between the results of the two algorithms that obtained a better performance, the authors pointed out that the classification speed was much higher after applying the PCA technique in reducing the dimensionality of the NSL-KDD dataset [9]. Thus, the need for optimizing the dataset is confirmed according to [16], [45], [52]- [54].…”
Section: Related Workmentioning
confidence: 99%
“…An intrusion detection dataset can be established by collecting network traffic features from different sources, such as network traffic flows containing information about the host, user behavior, and system configurations [81][82][83]. This information is required to study the attack patterns and abnormal activity of various network attacks.…”
Section: Intrusion Detection Datasetmentioning
confidence: 99%
“…Input data are a crucial factor in producing a decent classification. Based on research surveys conducted in [1][2][3], the progress of optimizing the intrusion detection models with the concept of machine learning requires a reliable dataset. Malowidzki et al [1] argue that the lack of a proper dataset for research causes difficulty in evaluating methods and comparing the performance of research results.…”
Section: Introductionmentioning
confidence: 99%
“…The NSL-KDD dataset has comparable data and labels in its evaluation, but the amount of data is not balanced. Thakkar and Lohiya [3] also reveal that NSL-KDD has a few types of attacks, and the amount of data from each attack is not equal. In the machine learning environment, input is significant for improving classification results.…”
Section: Introductionmentioning
confidence: 99%