Detecting Insider Threats with Machine Learning Algorithms

Author

Sule Simsek
Ralph W. Wilkerson, Missouri University of Science and TechnologyFollow
R. Joe Stanley, Missouri University of Science and TechnologyFollow

Abstract

Computer attacks are often caused by the insider threats. Therefore, building computer systems that are less vulnerable to insider attacks becomes a crucial problem. In this paper, the machine learning program, C4.5 and the rule-learning algorithm, RIPPER were used for detecting insider threats. These techniques were applied to detect misuse intrusions in a distributed system. The patterns of system behavior and the set of related system features were used to learn classifiers that can recognize known intrusions. In this paper, the performances of these techniques were compared and presented.

Recommended Citation

S. Simsek et al., "Detecting Insider Threats with Machine Learning Algorithms," MCCSIS 2007 - IADIS Multi Conference on Computer Science and Information Systems - Proceedings of Wireless Applications and Computing 2007, Telecommunications, Networks and Systems 2007 and Data Mining 2007, pp. 150 - 154, The Open University, Jan 2020.

Department(s)

Computer Science

Second Department

Electrical and Computer Engineering

Keywords and Phrases

Classification; Data streams mining; Distributed systems; Intrusion detection

International Standard Book Number (ISBN)

978-972892440-9

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 The Open University, All rights reserved.

Publication Date

01 Jan 2020