The development of an efficient detection mechanism to determine malicious network traffic has been a critical research topic in the field of network security in recent years. This study implemented an intrusion-detection system (IDS) based on a machine learning algorithm to periodically convert and analyze real network traffic in the campus environment in almost real time. The focuses of this study are on determining how to improve the detection rate of an IDS and how to detect more non-well-known port attacks apart from the traditional rule-based system. Four new features are used to increase the discriminant accuracy. In addition, an algorithm for balancing the data set was used to construct the training data set, which can also enable the learning model to more accurately reflect situations in real environment.
Cheng-Chung KUO
National Cheng Kung University
Ding-Kai TSENG
National Cheng Kung University
Chun-Wei TSAI
National Sun Yat Sen University
Chu-Sing YANG
National Cheng Kung University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Cheng-Chung KUO, Ding-Kai TSENG, Chun-Wei TSAI, Chu-Sing YANG, "An Effective Feature Extraction Mechanism for Intrusion Detection System" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 11, pp. 1814-1827, November 2021, doi: 10.1587/transinf.2021NGP0007.
Abstract: The development of an efficient detection mechanism to determine malicious network traffic has been a critical research topic in the field of network security in recent years. This study implemented an intrusion-detection system (IDS) based on a machine learning algorithm to periodically convert and analyze real network traffic in the campus environment in almost real time. The focuses of this study are on determining how to improve the detection rate of an IDS and how to detect more non-well-known port attacks apart from the traditional rule-based system. Four new features are used to increase the discriminant accuracy. In addition, an algorithm for balancing the data set was used to construct the training data set, which can also enable the learning model to more accurately reflect situations in real environment.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021NGP0007/_p
Copy
@ARTICLE{e104-d_11_1814,
author={Cheng-Chung KUO, Ding-Kai TSENG, Chun-Wei TSAI, Chu-Sing YANG, },
journal={IEICE TRANSACTIONS on Information},
title={An Effective Feature Extraction Mechanism for Intrusion Detection System},
year={2021},
volume={E104-D},
number={11},
pages={1814-1827},
abstract={The development of an efficient detection mechanism to determine malicious network traffic has been a critical research topic in the field of network security in recent years. This study implemented an intrusion-detection system (IDS) based on a machine learning algorithm to periodically convert and analyze real network traffic in the campus environment in almost real time. The focuses of this study are on determining how to improve the detection rate of an IDS and how to detect more non-well-known port attacks apart from the traditional rule-based system. Four new features are used to increase the discriminant accuracy. In addition, an algorithm for balancing the data set was used to construct the training data set, which can also enable the learning model to more accurately reflect situations in real environment.},
keywords={},
doi={10.1587/transinf.2021NGP0007},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - An Effective Feature Extraction Mechanism for Intrusion Detection System
T2 - IEICE TRANSACTIONS on Information
SP - 1814
EP - 1827
AU - Cheng-Chung KUO
AU - Ding-Kai TSENG
AU - Chun-Wei TSAI
AU - Chu-Sing YANG
PY - 2021
DO - 10.1587/transinf.2021NGP0007
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2021
AB - The development of an efficient detection mechanism to determine malicious network traffic has been a critical research topic in the field of network security in recent years. This study implemented an intrusion-detection system (IDS) based on a machine learning algorithm to periodically convert and analyze real network traffic in the campus environment in almost real time. The focuses of this study are on determining how to improve the detection rate of an IDS and how to detect more non-well-known port attacks apart from the traditional rule-based system. Four new features are used to increase the discriminant accuracy. In addition, an algorithm for balancing the data set was used to construct the training data set, which can also enable the learning model to more accurately reflect situations in real environment.
ER -