A convolutional neural-based learning classifier system for detecting database intrusion via insider attack

Seok Jun Bu, Sung Bae Cho

Research output: Contribution to journalArticle

Abstract

Role-based access control (RBAC) in databases provides a valuable level of abstraction to promote security administration at the business enterprise level. With the capacity for adaptation and learning, machine learning algorithms are suitable for modeling normal data access patterns based on large amounts of data and presenting robust statistical models that are not sensitive to user changes. We propose a convolutional neural-based learning classifier system (CN-LCS) that models the role of queries by combining conventional learning classifier system (LCS) with convolutional neural network (CNN) for a database intrusion detection system based on the RBAC mechanism. The combination of modified Pittsburgh-style LCSs for the optimization of feature selection rules and one-dimensional CNNs for modeling and classification in place of traditional rule generation outperforms other machine learning classifiers on a synthetic query dataset. In order to quantitatively compare the inclusion of rule generation and modeling processes in the CN-LCS, we have conducted 10-fold cross-validation tests and analysis through a paired sampled t-test.

Original languageEnglish
Pages (from-to)123-136
Number of pages14
JournalInformation sciences
Volume512
DOIs
Publication statusPublished - 2020 Feb

Fingerprint

Learning Classifier Systems
Rule Generation
Role-based Access Control
Classifiers
Attack
Machine Learning
Access control
Query
Learning systems
Selection Rules
t-test
Intrusion Detection
Process Modeling
Modeling
Cross-validation
Feature Selection
Statistical Model
Learning Algorithm
Intrusion detection
Fold

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

@article{58d9a9e6b9fb4add9fc65c6ac41dccd7,
title = "A convolutional neural-based learning classifier system for detecting database intrusion via insider attack",
abstract = "Role-based access control (RBAC) in databases provides a valuable level of abstraction to promote security administration at the business enterprise level. With the capacity for adaptation and learning, machine learning algorithms are suitable for modeling normal data access patterns based on large amounts of data and presenting robust statistical models that are not sensitive to user changes. We propose a convolutional neural-based learning classifier system (CN-LCS) that models the role of queries by combining conventional learning classifier system (LCS) with convolutional neural network (CNN) for a database intrusion detection system based on the RBAC mechanism. The combination of modified Pittsburgh-style LCSs for the optimization of feature selection rules and one-dimensional CNNs for modeling and classification in place of traditional rule generation outperforms other machine learning classifiers on a synthetic query dataset. In order to quantitatively compare the inclusion of rule generation and modeling processes in the CN-LCS, we have conducted 10-fold cross-validation tests and analysis through a paired sampled t-test.",
author = "Bu, {Seok Jun} and Cho, {Sung Bae}",
year = "2020",
month = "2",
doi = "10.1016/j.ins.2019.09.055",
language = "English",
volume = "512",
pages = "123--136",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

A convolutional neural-based learning classifier system for detecting database intrusion via insider attack. / Bu, Seok Jun; Cho, Sung Bae.

In: Information sciences, Vol. 512, 02.2020, p. 123-136.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A convolutional neural-based learning classifier system for detecting database intrusion via insider attack

AU - Bu, Seok Jun

AU - Cho, Sung Bae

PY - 2020/2

Y1 - 2020/2

N2 - Role-based access control (RBAC) in databases provides a valuable level of abstraction to promote security administration at the business enterprise level. With the capacity for adaptation and learning, machine learning algorithms are suitable for modeling normal data access patterns based on large amounts of data and presenting robust statistical models that are not sensitive to user changes. We propose a convolutional neural-based learning classifier system (CN-LCS) that models the role of queries by combining conventional learning classifier system (LCS) with convolutional neural network (CNN) for a database intrusion detection system based on the RBAC mechanism. The combination of modified Pittsburgh-style LCSs for the optimization of feature selection rules and one-dimensional CNNs for modeling and classification in place of traditional rule generation outperforms other machine learning classifiers on a synthetic query dataset. In order to quantitatively compare the inclusion of rule generation and modeling processes in the CN-LCS, we have conducted 10-fold cross-validation tests and analysis through a paired sampled t-test.

AB - Role-based access control (RBAC) in databases provides a valuable level of abstraction to promote security administration at the business enterprise level. With the capacity for adaptation and learning, machine learning algorithms are suitable for modeling normal data access patterns based on large amounts of data and presenting robust statistical models that are not sensitive to user changes. We propose a convolutional neural-based learning classifier system (CN-LCS) that models the role of queries by combining conventional learning classifier system (LCS) with convolutional neural network (CNN) for a database intrusion detection system based on the RBAC mechanism. The combination of modified Pittsburgh-style LCSs for the optimization of feature selection rules and one-dimensional CNNs for modeling and classification in place of traditional rule generation outperforms other machine learning classifiers on a synthetic query dataset. In order to quantitatively compare the inclusion of rule generation and modeling processes in the CN-LCS, we have conducted 10-fold cross-validation tests and analysis through a paired sampled t-test.

UR - http://www.scopus.com/inward/record.url?scp=85072785609&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072785609&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2019.09.055

DO - 10.1016/j.ins.2019.09.055

M3 - Article

AN - SCOPUS:85072785609

VL - 512

SP - 123

EP - 136

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -