With the growth in the use of the Internet and local area networks, malicious attacks and intrusions into
computer systems are increasing. Implementing intrusion detection systems have become extremely
important to help maintain good network security. Support vector machines (SVMs), a classic pattern
recognition tool, have been widely used in intrusion detection. They can handle very large data with high
efficiency, are easy to use, and exhibit good prediction behavior. This paper presents a new SVM model
enriched with a Gaussian kernel function based on the features of the training data for intrusion detection.
The new model is tested with the CICIDS2017 dataset. The test proves better results in terms of detection
efficiency and false alarm rate, which can give better coverage and make detection more efficient.
%0 Journal Article
%1 noauthororeditor
%A Elaeraj, Ouafae
%A Leghris, Cherkaoui
%D 2021
%J International Journal on Cryptography and Information Security (IJCIS)
%K cryptography
%N 2/3
%P 14
%R https://doi.org/10.5121/ijcis.2021.11401
%T Progress of Machine Learning in the Field of Intrusion Detection Systems
%U https://wireilla.com/papers/ijcis/V11N4/11421ijcis01.pdf
%V 11
%X With the growth in the use of the Internet and local area networks, malicious attacks and intrusions into
computer systems are increasing. Implementing intrusion detection systems have become extremely
important to help maintain good network security. Support vector machines (SVMs), a classic pattern
recognition tool, have been widely used in intrusion detection. They can handle very large data with high
efficiency, are easy to use, and exhibit good prediction behavior. This paper presents a new SVM model
enriched with a Gaussian kernel function based on the features of the training data for intrusion detection.
The new model is tested with the CICIDS2017 dataset. The test proves better results in terms of detection
efficiency and false alarm rate, which can give better coverage and make detection more efficient.
@article{noauthororeditor,
abstract = {With the growth in the use of the Internet and local area networks, malicious attacks and intrusions into
computer systems are increasing. Implementing intrusion detection systems have become extremely
important to help maintain good network security. Support vector machines (SVMs), a classic pattern
recognition tool, have been widely used in intrusion detection. They can handle very large data with high
efficiency, are easy to use, and exhibit good prediction behavior. This paper presents a new SVM model
enriched with a Gaussian kernel function based on the features of the training data for intrusion detection.
The new model is tested with the CICIDS2017 dataset. The test proves better results in terms of detection
efficiency and false alarm rate, which can give better coverage and make detection more efficient. },
added-at = {2022-01-12T11:42:45.000+0100},
author = {Elaeraj, Ouafae and Leghris, Cherkaoui},
biburl = {https://www.bibsonomy.org/bibtex/2b3c2432db7a670c7aca89b6921e720d1/alinta},
doi = {https://doi.org/10.5121/ijcis.2021.11401},
interhash = {af4116c93823fae9a8ed352a2becf534},
intrahash = {b3c2432db7a670c7aca89b6921e720d1},
journal = {International Journal on Cryptography and Information Security (IJCIS)},
keywords = {cryptography},
language = {English},
month = {September},
number = {2/3},
pages = 14,
timestamp = {2022-01-12T11:42:45.000+0100},
title = {Progress of Machine Learning in the Field of Intrusion Detection Systems},
url = {https://wireilla.com/papers/ijcis/V11N4/11421ijcis01.pdf},
volume = 11,
year = 2021
}