2016
DOI: 10.1080/19393555.2015.1125974
|View full text |Cite
|
Sign up to set email alerts
|

The evaluation of Network Anomaly Detection Systems: Statistical analysis of the UNSW-NB15 data set and the comparison with the KDD99 data set

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

2
392
0
13

Year Published

2017
2017
2022
2022

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 678 publications
(407 citation statements)
references
References 18 publications
2
392
0
13
Order By: Relevance
“…Bu çalışma kapsamında kullanılan veri kümesi, Avustralya Siber Güvenlik Merkezi'nde bulunan Siber Güvenlik Laboratuvarından alınmıştır [14]. …”
Section: Veri Kümesiunclassified
“…Bu çalışma kapsamında kullanılan veri kümesi, Avustralya Siber Güvenlik Merkezi'nde bulunan Siber Güvenlik Laboratuvarından alınmıştır [14]. …”
Section: Veri Kümesiunclassified
“…Failing to do so does not contribute to IDS research even if the system reliably detects all attacks showing the best possible capabilities. It has also been reported that the results of such contributions become irrelevant mostly when performed cross-validation with contemporary workloads [35]. Therefore, the models and evaluations based exclusively on outdated datasets place a shadow of doubt on their usefulness and also impair the ability to explore further knowledge horizons.…”
Section: Background and Related Workmentioning
confidence: 99%
“…This dataset was utilized in [5] for statistical and evaluation purposes by comparing five different algorithms DT, LR, NB, ANN, and EM clustering, for measuring their performance in terms of accuracy and False Alarm Rate (FAR) against the KDD99 dataset. The evaluation results showed that the DT technique achieved the best efficiency.…”
Section: Related Workmentioning
confidence: 99%
“…The authors in [24] apply a combining classifier with NBTree and RandomTree algorithm in the NSL-KDD dataset for detecting the normal and attack traffic with an achieved accuracy of 89,24% along 41 attributes. In [5], a different multiclass classifier is applied to identify normal traffic or nine attack types: Fuzzers, Analysis, Backdoor, DoS, Exploit, Generic, Reconnaissance, Shellcode and Worm. The highest result of 85,56% was achieved using a Decision Tree algorithm with all the attributes.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation