Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy

Ashraf Mohammed Saeed; Zaid Alyafeai; Ashraf Mahmoud

doi:10.1109/CICN56167.2022.10008309

Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy

Ashraf Mohammed Saeed, Zaid Alyafeai, Ashraf Mahmoud

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Intrusion detection systems (IDS) have been used to identify several types of attacks. Several issues can affect the classification of attacks, such as classification results which can be biased due to unbalanced data that have been used in the training of the classifier. Moreover, the detection rate of these IDS has to be improved to detect as many as possible of several attacks. In this paper, we propose to use a complex sequential model such as Gated Recurrent Units to classify different kinds of attacks. We use the NSL-KDD dataset to train our model. This dataset has unbalanced data which might affect the results of our classifier. To fix this issue, we use Dropout and weighted cross entropy loss function to overcome the issue of unbalanced data. Our results show that there is an enhancement in the detection rate of the classifier. we have achieved a higher detection rate compared with previous studies.

Original language	English
Title of host publication	Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	218-223
Number of pages	6
ISBN (Electronic)	9781665487719
DOIs	https://doi.org/10.1109/CICN56167.2022.10008309
State	Published - 2022
Event	14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022 - Al-Khobar, Saudi Arabia Duration: 4 Dec 2022 → 6 Dec 2022

Publication series

Name	Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022

Conference

Conference	14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022
Country/Territory	Saudi Arabia
City	Al-Khobar
Period	4/12/22 → 6/12/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Deep Network
GRU
IDS

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Computer Vision and Pattern Recognition

Access to Document

10.1109/CICN56167.2022.10008309

Cite this

Saeed, A. M., Alyafeai, Z., & Mahmoud, A. (2022). Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy. In Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022 (pp. 218-223). (Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CICN56167.2022.10008309

Saeed, Ashraf Mohammed ; Alyafeai, Zaid ; Mahmoud, Ashraf. / Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy. Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 218-223 (Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022).

@inproceedings{013ec7e4c9014183ad60b49dc1e98543,

title = "Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy",

abstract = "Intrusion detection systems (IDS) have been used to identify several types of attacks. Several issues can affect the classification of attacks, such as classification results which can be biased due to unbalanced data that have been used in the training of the classifier. Moreover, the detection rate of these IDS has to be improved to detect as many as possible of several attacks. In this paper, we propose to use a complex sequential model such as Gated Recurrent Units to classify different kinds of attacks. We use the NSL-KDD dataset to train our model. This dataset has unbalanced data which might affect the results of our classifier. To fix this issue, we use Dropout and weighted cross entropy loss function to overcome the issue of unbalanced data. Our results show that there is an enhancement in the detection rate of the classifier. we have achieved a higher detection rate compared with previous studies.",

keywords = "Deep Network, GRU, IDS",

author = "Saeed, \{Ashraf Mohammed\} and Zaid Alyafeai and Ashraf Mahmoud",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022 ; Conference date: 04-12-2022 Through 06-12-2022",

year = "2022",

doi = "10.1109/CICN56167.2022.10008309",

language = "English",

series = "Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "218--223",

booktitle = "Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022",

address = "United States",

}

Saeed, AM, Alyafeai, Z & Mahmoud, A 2022, Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy. in Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022. Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022, Institute of Electrical and Electronics Engineers Inc., pp. 218-223, 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022, Al-Khobar, Saudi Arabia, 4/12/22. https://doi.org/10.1109/CICN56167.2022.10008309

Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy. / Saeed, Ashraf Mohammed; Alyafeai, Zaid; Mahmoud, Ashraf.
Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 218-223 (Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy

AU - Saeed, Ashraf Mohammed

AU - Alyafeai, Zaid

AU - Mahmoud, Ashraf

PY - 2022

Y1 - 2022

N2 - Intrusion detection systems (IDS) have been used to identify several types of attacks. Several issues can affect the classification of attacks, such as classification results which can be biased due to unbalanced data that have been used in the training of the classifier. Moreover, the detection rate of these IDS has to be improved to detect as many as possible of several attacks. In this paper, we propose to use a complex sequential model such as Gated Recurrent Units to classify different kinds of attacks. We use the NSL-KDD dataset to train our model. This dataset has unbalanced data which might affect the results of our classifier. To fix this issue, we use Dropout and weighted cross entropy loss function to overcome the issue of unbalanced data. Our results show that there is an enhancement in the detection rate of the classifier. we have achieved a higher detection rate compared with previous studies.

AB - Intrusion detection systems (IDS) have been used to identify several types of attacks. Several issues can affect the classification of attacks, such as classification results which can be biased due to unbalanced data that have been used in the training of the classifier. Moreover, the detection rate of these IDS has to be improved to detect as many as possible of several attacks. In this paper, we propose to use a complex sequential model such as Gated Recurrent Units to classify different kinds of attacks. We use the NSL-KDD dataset to train our model. This dataset has unbalanced data which might affect the results of our classifier. To fix this issue, we use Dropout and weighted cross entropy loss function to overcome the issue of unbalanced data. Our results show that there is an enhancement in the detection rate of the classifier. we have achieved a higher detection rate compared with previous studies.

KW - Deep Network

KW - GRU

KW - IDS

UR - https://www.scopus.com/pages/publications/85146844592

U2 - 10.1109/CICN56167.2022.10008309

DO - 10.1109/CICN56167.2022.10008309

M3 - Conference contribution

AN - SCOPUS:85146844592

T3 - Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022

SP - 218

EP - 223

BT - Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022

Y2 - 4 December 2022 through 6 December 2022

ER -

Saeed AM, Alyafeai Z, Mahmoud A. Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy. In Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 218-223. (Proceedings - 2022 14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022). doi: 10.1109/CICN56167.2022.10008309

Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this