Novel attack detection using fuzzy logic and data mining

N.B. Idris, B. Shanmugam

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

Abstract

Intrusion Detection Systems are increasingly a key part of systems defense. Various approaches to Intrusion Detection are currently being used, but they are relatively ineffective. Artificial Intelligence plays a driving role in security services. This paper proposes a dynamic Intelligent Intrusion Detection System model, based on specific AI approach for intrusion detection. The technique that is being investigated includes fuzzy logic with network profiling, which uses simple data mining techniques to process the network data. The proposed hybrid system combines anomaly and misuse detection. Simple fuzzy rules, allow us to construct if-then rules that reflect common ways of describing security attacks. Suspicious intrusions can be traced back to its original source and any traffic from that particular source will be redirected back to them in future. Both network traffic and system audit data are used as inputs for the experimental needs.
Original languageEnglish
Title of host publicationProceedings of The 2006 International Conference on Security and Management, SAM'06
Number of pages6
Publication statusPublished - 2006
Externally publishedYes
Event2006 International Conference on Security and Management - Las Vegas, NV; United States
Duration: 26 Jun 200629 Jun 2006
Conference number: 75578

Conference

Conference2006 International Conference on Security and Management
Abbreviated titleSAM'06
Period26/06/0629/06/06

Fingerprint

Intrusion detection
Fuzzy logic
Data mining
Fuzzy rules
Hybrid systems
Artificial intelligence

Cite this

Idris, N. B., & Shanmugam, B. (2006). Novel attack detection using fuzzy logic and data mining. In Proceedings of The 2006 International Conference on Security and Management, SAM'06
Idris, N.B. ; Shanmugam, B. / Novel attack detection using fuzzy logic and data mining. Proceedings of The 2006 International Conference on Security and Management, SAM'06. 2006.
@inproceedings{943436013a5e4081af8e053e8f2e73f7,
title = "Novel attack detection using fuzzy logic and data mining",
abstract = "Intrusion Detection Systems are increasingly a key part of systems defense. Various approaches to Intrusion Detection are currently being used, but they are relatively ineffective. Artificial Intelligence plays a driving role in security services. This paper proposes a dynamic Intelligent Intrusion Detection System model, based on specific AI approach for intrusion detection. The technique that is being investigated includes fuzzy logic with network profiling, which uses simple data mining techniques to process the network data. The proposed hybrid system combines anomaly and misuse detection. Simple fuzzy rules, allow us to construct if-then rules that reflect common ways of describing security attacks. Suspicious intrusions can be traced back to its original source and any traffic from that particular source will be redirected back to them in future. Both network traffic and system audit data are used as inputs for the experimental needs.",
keywords = "Attack detections, Data mining techniques, If-then rules, Intelligent Intrusion detection systems, Intrusion detection systems, Key parts, Misuse detections, Network datum, Network traffics, Security attacks, Security services, System audits, Artificial intelligence, Computer crime, Data mining, Fuzzy logic, Fuzzy sets, Information management, Internet, Model structures, Intrusion detection",
author = "N.B. Idris and B. Shanmugam",
year = "2006",
language = "English",
isbn = "978-160132001-8",
booktitle = "Proceedings of The 2006 International Conference on Security and Management, SAM'06",

}

Idris, NB & Shanmugam, B 2006, Novel attack detection using fuzzy logic and data mining. in Proceedings of The 2006 International Conference on Security and Management, SAM'06. 2006 International Conference on Security and Management, 26/06/06.

Novel attack detection using fuzzy logic and data mining. / Idris, N.B.; Shanmugam, B.

Proceedings of The 2006 International Conference on Security and Management, SAM'06. 2006.

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

TY - GEN

T1 - Novel attack detection using fuzzy logic and data mining

AU - Idris, N.B.

AU - Shanmugam, B.

PY - 2006

Y1 - 2006

N2 - Intrusion Detection Systems are increasingly a key part of systems defense. Various approaches to Intrusion Detection are currently being used, but they are relatively ineffective. Artificial Intelligence plays a driving role in security services. This paper proposes a dynamic Intelligent Intrusion Detection System model, based on specific AI approach for intrusion detection. The technique that is being investigated includes fuzzy logic with network profiling, which uses simple data mining techniques to process the network data. The proposed hybrid system combines anomaly and misuse detection. Simple fuzzy rules, allow us to construct if-then rules that reflect common ways of describing security attacks. Suspicious intrusions can be traced back to its original source and any traffic from that particular source will be redirected back to them in future. Both network traffic and system audit data are used as inputs for the experimental needs.

AB - Intrusion Detection Systems are increasingly a key part of systems defense. Various approaches to Intrusion Detection are currently being used, but they are relatively ineffective. Artificial Intelligence plays a driving role in security services. This paper proposes a dynamic Intelligent Intrusion Detection System model, based on specific AI approach for intrusion detection. The technique that is being investigated includes fuzzy logic with network profiling, which uses simple data mining techniques to process the network data. The proposed hybrid system combines anomaly and misuse detection. Simple fuzzy rules, allow us to construct if-then rules that reflect common ways of describing security attacks. Suspicious intrusions can be traced back to its original source and any traffic from that particular source will be redirected back to them in future. Both network traffic and system audit data are used as inputs for the experimental needs.

KW - Attack detections

KW - Data mining techniques

KW - If-then rules

KW - Intelligent Intrusion detection systems

KW - Intrusion detection systems

KW - Key parts

KW - Misuse detections

KW - Network datum

KW - Network traffics

KW - Security attacks

KW - Security services

KW - System audits

KW - Artificial intelligence

KW - Computer crime

KW - Data mining

KW - Fuzzy logic

KW - Fuzzy sets

KW - Information management

KW - Internet

KW - Model structures

KW - Intrusion detection

M3 - Conference Paper published in Proceedings

SN - 978-160132001-8

BT - Proceedings of The 2006 International Conference on Security and Management, SAM'06

ER -

Idris NB, Shanmugam B. Novel attack detection using fuzzy logic and data mining. In Proceedings of The 2006 International Conference on Security and Management, SAM'06. 2006