Performance analysis of an Intrusion Detection System using Panjab University Intrusion DataSet

Raman Singh; Harish Kumar; R.K. Singla

doi:10.1109/RAECS.2015.7453280

Performance analysis of an Intrusion Detection System using Panjab University Intrusion DataSet

Raman Singh, Harish Kumar, R.K. Singla

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

3 Citations (Scopus)

Abstract

Intrusion Detection System (IDS) can be used to detect malware by its network activities or behavioral profiles. Common challenges for IDS are large amount of data to process, low detection rate and high rate of false alarms. Online Sequential Extreme Learning Machine (OS-ELM) based IDS with network traffic profiling is tested on Panjab University - Intrusion DataSet (PU-IDataSet). This IDS is known as alpha-FST-Beta IDS. The training connections are first categorized on the basis of protocol and service features. This categorization is named as alpha profiling. It increases the scalability and reduces the time complexity of IDS. Large feature set of network traffic dataset is reduced using ensemble of three feature selection techniques. Beta profiling is used to reduce the size of training dataset. Various parameters like accuracy, true positive rate, false positive rate, true negative rate, false negative rate, precision, F1-score and detection time is used to evaluate the performance. The results obtained encourage the integration of this system in intrusion detection models.

Original language	English
Title of host publication	2015 2nd International Conference on Recent Advances in Engineering and Computational Sciences (RAECS)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9781467382533
ISBN (Print)	9781467382526
DOIs	https://doi.org/10.1109/RAECS.2015.7453280
Publication status	Published - 19 Apr 2016
Externally published	Yes
Event	2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences - Chandigarh, India Duration: 21 Dec 2015 → 22 Dec 2015

Conference

Conference	2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences
Abbreviated title	RAECS 2015
Country/Territory	India
City	Chandigarh
Period	21/12/15 → 22/12/15

Keywords

intrusion detection system
network traffic profiling
sampling
feature selection technique
inline sequential extreme learning machine
PU-IDataSet

Access to Document

10.1109/RAECS.2015.7453280

Cite this

@inproceedings{0bb80821fa584609ae1050c05ee85259,

title = "Performance analysis of an Intrusion Detection System using Panjab University Intrusion DataSet",

abstract = "Intrusion Detection System (IDS) can be used to detect malware by its network activities or behavioral profiles. Common challenges for IDS are large amount of data to process, low detection rate and high rate of false alarms. Online Sequential Extreme Learning Machine (OS-ELM) based IDS with network traffic profiling is tested on Panjab University - Intrusion DataSet (PU-IDataSet). This IDS is known as alpha-FST-Beta IDS. The training connections are first categorized on the basis of protocol and service features. This categorization is named as alpha profiling. It increases the scalability and reduces the time complexity of IDS. Large feature set of network traffic dataset is reduced using ensemble of three feature selection techniques. Beta profiling is used to reduce the size of training dataset. Various parameters like accuracy, true positive rate, false positive rate, true negative rate, false negative rate, precision, F1-score and detection time is used to evaluate the performance. The results obtained encourage the integration of this system in intrusion detection models.",

keywords = "intrusion detection system, network traffic profiling, sampling, feature selection technique, inline sequential extreme learning machine, PU-IDataSet",

author = "Raman Singh and Harish Kumar and R.K. Singla",

year = "2016",

month = apr,

day = "19",

doi = "10.1109/RAECS.2015.7453280",

language = "English",

isbn = "9781467382526",

booktitle = "2015 2nd International Conference on Recent Advances in Engineering and Computational Sciences (RAECS)",

publisher = "IEEE",

address = "United States",

note = "2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences, RAECS 2015 ; Conference date: 21-12-2015 Through 22-12-2015",

}

Singh, R, Kumar, H & Singla, RK 2016, Performance analysis of an Intrusion Detection System using Panjab University Intrusion DataSet. in 2015 2nd International Conference on Recent Advances in Engineering and Computational Sciences (RAECS). IEEE, Piscataway, NJ, 2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences, Chandigarh, India, 21/12/15. https://doi.org/10.1109/RAECS.2015.7453280

Performance analysis of an Intrusion Detection System using Panjab University Intrusion DataSet. / Singh, Raman; Kumar, Harish; Singla, R.K.
2015 2nd International Conference on Recent Advances in Engineering and Computational Sciences (RAECS). Piscataway, NJ: IEEE, 2016.

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

TY - GEN

T1 - Performance analysis of an Intrusion Detection System using Panjab University Intrusion DataSet

AU - Singh, Raman

AU - Kumar, Harish

AU - Singla, R.K.

PY - 2016/4/19

Y1 - 2016/4/19

N2 - Intrusion Detection System (IDS) can be used to detect malware by its network activities or behavioral profiles. Common challenges for IDS are large amount of data to process, low detection rate and high rate of false alarms. Online Sequential Extreme Learning Machine (OS-ELM) based IDS with network traffic profiling is tested on Panjab University - Intrusion DataSet (PU-IDataSet). This IDS is known as alpha-FST-Beta IDS. The training connections are first categorized on the basis of protocol and service features. This categorization is named as alpha profiling. It increases the scalability and reduces the time complexity of IDS. Large feature set of network traffic dataset is reduced using ensemble of three feature selection techniques. Beta profiling is used to reduce the size of training dataset. Various parameters like accuracy, true positive rate, false positive rate, true negative rate, false negative rate, precision, F1-score and detection time is used to evaluate the performance. The results obtained encourage the integration of this system in intrusion detection models.

AB - Intrusion Detection System (IDS) can be used to detect malware by its network activities or behavioral profiles. Common challenges for IDS are large amount of data to process, low detection rate and high rate of false alarms. Online Sequential Extreme Learning Machine (OS-ELM) based IDS with network traffic profiling is tested on Panjab University - Intrusion DataSet (PU-IDataSet). This IDS is known as alpha-FST-Beta IDS. The training connections are first categorized on the basis of protocol and service features. This categorization is named as alpha profiling. It increases the scalability and reduces the time complexity of IDS. Large feature set of network traffic dataset is reduced using ensemble of three feature selection techniques. Beta profiling is used to reduce the size of training dataset. Various parameters like accuracy, true positive rate, false positive rate, true negative rate, false negative rate, precision, F1-score and detection time is used to evaluate the performance. The results obtained encourage the integration of this system in intrusion detection models.

KW - intrusion detection system

KW - network traffic profiling

KW - sampling

KW - feature selection technique

KW - inline sequential extreme learning machine

KW - PU-IDataSet

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-84966344961&partnerID=MN8TOARS

U2 - 10.1109/RAECS.2015.7453280

DO - 10.1109/RAECS.2015.7453280

M3 - Conference contribution

SN - 9781467382526

BT - 2015 2nd International Conference on Recent Advances in Engineering and Computational Sciences (RAECS)

PB - IEEE

CY - Piscataway, NJ

T2 - 2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences

Y2 - 21 December 2015 through 22 December 2015

ER -

Performance analysis of an Intrusion Detection System using Panjab University Intrusion DataSet

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this