Automated network feature weighting-based anomaly detection

Dat Tran; Wanli Ma; Dharmendra Sharma

doi:10.1109/ISI.2008.4565047

Automated network feature weighting-based anomaly detection

Dat Tran, Wanli Ma, Dharmendra Sharma

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

We propose in this paper an automated feature weighting method based on fuzzy subspace approach to assign a weight to each network feature depending on its degree of importance in anomaly detection. Fuzzy c-means and fuzzy entropy modeling are used to calculate weight values and k-means vector quantization is used to model network patterns. The proposed method not only increases the detection rate but also reduces false alarm rate as shown in our experiments.

Original language	English
Title of host publication	2008 IEEE International Conference on Intelligence and Security Informatics
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	162-166
Number of pages	5
DOIs	https://doi.org/10.1109/ISI.2008.4565047
Publication status	Published - 2008
Event	IEEE International Conference on Intelligence and Security Informatics, 2008, IEEE ISI 2008 - Taipei, Taiwan, Province of China Duration: 17 Jun 2008 → 20 Jun 2008

Conference

Conference	IEEE International Conference on Intelligence and Security Informatics, 2008, IEEE ISI 2008
Country/Territory	Taiwan, Province of China
City	Taipei
Period	17/06/08 → 20/06/08

Access to Document

10.1109/ISI.2008.4565047

Cite this

@inproceedings{97ea8479278a41d682672bed74b1d438,

title = "Automated network feature weighting-based anomaly detection",

abstract = "We propose in this paper an automated feature weighting method based on fuzzy subspace approach to assign a weight to each network feature depending on its degree of importance in anomaly detection. Fuzzy c-means and fuzzy entropy modeling are used to calculate weight values and k-means vector quantization is used to model network patterns. The proposed method not only increases the detection rate but also reduces false alarm rate as shown in our experiments.",

keywords = "Automated feature weighting, Fuzzy entropy, Network anomaly detection, Subspace vector quantization, fuzzy c-means",

author = "Dat Tran and Wanli Ma and Dharmendra Sharma",

year = "2008",

doi = "10.1109/ISI.2008.4565047",

language = "English",

pages = "162--166",

booktitle = "2008 IEEE International Conference on Intelligence and Security Informatics",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "IEEE International Conference on Intelligence and Security Informatics, 2008, IEEE ISI 2008 ; Conference date: 17-06-2008 Through 20-06-2008",

}

Tran, D , Ma, W & Sharma, D 2008, Automated network feature weighting-based anomaly detection. in 2008 IEEE International Conference on Intelligence and Security Informatics. IEEE, Institute of Electrical and Electronics Engineers, pp. 162-166, IEEE International Conference on Intelligence and Security Informatics, 2008, IEEE ISI 2008, Taipei, Taiwan, Province of China, 17/06/08. https://doi.org/10.1109/ISI.2008.4565047

TY - GEN

T1 - Automated network feature weighting-based anomaly detection

AU - Tran, Dat

AU - Ma, Wanli

AU - Sharma, Dharmendra

PY - 2008

Y1 - 2008

N2 - We propose in this paper an automated feature weighting method based on fuzzy subspace approach to assign a weight to each network feature depending on its degree of importance in anomaly detection. Fuzzy c-means and fuzzy entropy modeling are used to calculate weight values and k-means vector quantization is used to model network patterns. The proposed method not only increases the detection rate but also reduces false alarm rate as shown in our experiments.

AB - We propose in this paper an automated feature weighting method based on fuzzy subspace approach to assign a weight to each network feature depending on its degree of importance in anomaly detection. Fuzzy c-means and fuzzy entropy modeling are used to calculate weight values and k-means vector quantization is used to model network patterns. The proposed method not only increases the detection rate but also reduces false alarm rate as shown in our experiments.

KW - Automated feature weighting

KW - Fuzzy entropy

KW - Network anomaly detection

KW - Subspace vector quantization, fuzzy c-means

UR - http://www.scopus.com/inward/record.url?scp=51849134951&partnerID=8YFLogxK

U2 - 10.1109/ISI.2008.4565047

DO - 10.1109/ISI.2008.4565047

M3 - Conference contribution

AN - SCOPUS:51849134951

SP - 162

EP - 166

BT - 2008 IEEE International Conference on Intelligence and Security Informatics

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE International Conference on Intelligence and Security Informatics, 2008, IEEE ISI 2008

Y2 - 17 June 2008 through 20 June 2008

ER -

Automated network feature weighting-based anomaly detection

Abstract

Conference

Access to Document

Other files and links

Cite this