Artificial Neural Networks to Misuse Detection

James D. Cannady

Artificial Neural Networks to Misuse Detection

James D. Cannady

Research output: Contribution to conference › Presentation

Abstract

Misuse detection is the process of attempting to identify instances of network attacks by comparing current activity against the expected actions of an intruder. Most current approaches to misuse detection involve the use of rule-based expert systems to identify indications of known attacks. However, these techniques are less successful in identifying attacks which vary from expected patterns. Artificial neural networks provide the potential to identify and classify network activity based on limited, incomplete, and nonlinear data sources. We present an approach to the process of misuse detection that utilizes the analytical strengths of neural networks, and we provide the results from our preliminary analysis of this approach.

Original language	American English
State	Published - Oct 1 1998
Event	Proceedings of the 21st National Information Systems Security Conference - Duration: Oct 1 1998 → …

Conference

Conference	Proceedings of the 21st National Information Systems Security Conference
Period	10/1/98 → …

Keywords

Intrusion detection
computer security
misuse detection
neural networks

Disciplines

Computer Sciences

Cite this

@conference{74e76746c0fc4366844b5ca755c03801,

title = "Artificial Neural Networks to Misuse Detection",

abstract = " Misuse detection is the process of attempting to identify instances of network attacks by comparing current activity against the expected actions of an intruder. Most current approaches to misuse detection involve the use of rule-based expert systems to identify indications of known attacks. However, these techniques are less successful in identifying attacks which vary from expected patterns. Artificial neural networks provide the potential to identify and classify network activity based on limited, incomplete, and nonlinear data sources. We present an approach to the process of misuse detection that utilizes the analytical strengths of neural networks, and we provide the results from our preliminary analysis of this approach.",

keywords = "Intrusion detection, computer security, misuse detection, neural networks",

author = "Cannady, \{James D.\}",

year = "1998",

month = oct,

day = "1",

language = "American English",

note = "Proceedings of the 21st National Information Systems Security Conference ; Conference date: 01-10-1998",

}

TY - CONF

T1 - Artificial Neural Networks to Misuse Detection

AU - Cannady, James D.

PY - 1998/10/1

Y1 - 1998/10/1

N2 - Misuse detection is the process of attempting to identify instances of network attacks by comparing current activity against the expected actions of an intruder. Most current approaches to misuse detection involve the use of rule-based expert systems to identify indications of known attacks. However, these techniques are less successful in identifying attacks which vary from expected patterns. Artificial neural networks provide the potential to identify and classify network activity based on limited, incomplete, and nonlinear data sources. We present an approach to the process of misuse detection that utilizes the analytical strengths of neural networks, and we provide the results from our preliminary analysis of this approach.

AB - Misuse detection is the process of attempting to identify instances of network attacks by comparing current activity against the expected actions of an intruder. Most current approaches to misuse detection involve the use of rule-based expert systems to identify indications of known attacks. However, these techniques are less successful in identifying attacks which vary from expected patterns. Artificial neural networks provide the potential to identify and classify network activity based on limited, incomplete, and nonlinear data sources. We present an approach to the process of misuse detection that utilizes the analytical strengths of neural networks, and we provide the results from our preliminary analysis of this approach.

KW - Intrusion detection

KW - computer security

KW - misuse detection

KW - neural networks

UR - https://nsuworks.nova.edu/gscis_facpres/563

M3 - Presentation

T2 - Proceedings of the 21st National Information Systems Security Conference

Y2 - 1 October 1998

ER -

Artificial Neural Networks to Misuse Detection

Abstract

Conference

Keywords

Disciplines

Other files and links

Fingerprint

Cite this