MISUSE DETECTION - A Neural Network vs. A Genetic Algorithm Approach

Pedro A. Diaz-Gomez, Dean F. Hougen

2007

Abstract

Misuse detection can be addressed as an optimization problem, where the problem is to find an array of possible intrusions x that maximizes a function f (·) subject to a constraint r imposed by a user’s actions performed on a computer. This position paper presents and compares two ways of finding x, in audit data, by using neural networks and genetic algorithms.

References

  1. Diaz-Gomez, P. A. and Hougen, D. F. (2005a). Analysis and mathematical justification of a fitness function used in an intrusion detection system. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 1591-1592.
  2. Diaz-Gomez, P. A. and Hougen, D. F. (2005b). Improved off-line intrusion detection using a genetic algorithm. In Proceedings of the 7th International Conference on Enterprise Information Systems, pages 66-73.
  3. Diaz-Gomez, P. A. and Hougen, D. F. (2006). A genetic algorithm approach for doing misuse detection in audit trail files. In Proceedings of the CIC-2006 International Conference on Computing, pages 329-335.
  4. Diaz-Gomez, P. A. and Hougen, D. F. (2007). Misuse detection: An iterative process vs. a genetic algorithm approach. In Proceedings of the 9th International Conference on Enterprise Information Systems.
  5. Ham, F. M. and Kostanic, I. (2001). Principles of Neurocomputing for Science & Engineering. Mc Graw Hill.
  6. Mé, L. (1993). Security audit trail analysis using genetic algorithms. In Proceedings of the 12th. International Conference on Computer Safety, Reliability, and Security, pages 329-340.
  7. Mé, L. (1998). GASSATA, a genetic algorithm as an alternative tool for security audit trail analysis. In Proceedings of the First International Workshop on the Recent Advances in Intrusion Detection.
Download


Paper Citation


in Harvard Style

A. Diaz-Gomez P. and F. Hougen D. (2007). MISUSE DETECTION - A Neural Network vs. A Genetic Algorithm Approach . In Proceedings of the Ninth International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-972-8865-89-4, pages 459-462. DOI: 10.5220/0002410904590462


in Bibtex Style

@conference{iceis07,
author={Pedro A. Diaz-Gomez and Dean F. Hougen},
title={MISUSE DETECTION - A Neural Network vs. A Genetic Algorithm Approach},
booktitle={Proceedings of the Ninth International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2007},
pages={459-462},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002410904590462},
isbn={978-972-8865-89-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Ninth International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - MISUSE DETECTION - A Neural Network vs. A Genetic Algorithm Approach
SN - 978-972-8865-89-4
AU - A. Diaz-Gomez P.
AU - F. Hougen D.
PY - 2007
SP - 459
EP - 462
DO - 10.5220/0002410904590462