A Pareto-based multi-objective evolutionary algorithm for automatic rule generation in network intrusion detection systems |
| |
Authors: | J. Gómez C. Gil R. Baños A. L. Márquez F. G. Montoya M. G. Montoya |
| |
Affiliation: | 1. Department of Languages and Computation, University of Almería, Carretera Sacramento s/n, Ca?ada San Urbano, 04120, Almería, Spain 2. Department of Computer Architecture and Electronics, University of Almería, Carretera Sacramento s/n, Ca?ada San Urbano, 04120, Almería, Spain 3. Department of Computer Architecture and Technology, University of Granada, Periodista Daniel Saucedo Aranda, s/n, 18071, Granada, Spain 4. Department of Rural Engineering, University of Almería, Carretera de Sacramento s/n, Ca?ada San Urbano, 04120, Almería, Spain
|
| |
Abstract: | Attacks against computer systems are becoming more complex, making it necessary to continually improve the security systems, such as intrusion detection systems which provide security for computer systems by distinguishing between hostile and non-hostile activity. Intrusion detection systems are usually classified into two main categories according to whether they are based on misuse (signature-based) detection or on anomaly detection. With the aim of minimizing the number of wrong decisions, a new Pareto-based multi-objective evolutionary algorithm is used to optimize the automatic rule generation of a signature-based intrusion detection system (IDS). This optimizer, included within a network IDS, has been evaluated using a benchmark dataset and real traffic of a Spanish university. The results obtained in this real application show the advantages of using this multi-objective approach. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|