Continuous Features Discretization for Anomaly Intrusion Detectors Generation
Network security is a growing issue, with the evolution of computer systems and expansion of attacks. Biological systems have been inspiring scientists and designs for new adaptive solutions, such as genetic algorithms. In this paper, an approach that use
- PDF / 763,113 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 28 Downloads / 227 Views
Abstract Network security is a growing issue, with the evolution of computer systems and expansion of attacks. Biological systems have been inspiring scientists and designs for new adaptive solutions, such as genetic algorithms. In this paper, an approach that uses the genetic algorithm to generate anomaly network intrusion detectors is used. An algorithm is proposed using a discretization method for the continuous features selection of intrusion detection, to create some homogeneity between values, which have different data types. Then, the intrusion detection system is tested against the NSL-KDD data set using different distance methods. A comparison is held amongst the results, and it is shown by the end that this proposed approach has good results, and recommendations are given for future experiments.
A. S. A. Aziz (&) French University in Egypt (UFE), Shorouk City, Egypt e-mail: [email protected] A. S. A. Aziz A. T. Azar Scientific Research Group in Egypt (SRGE), Cairo, Egypt e-mail: [email protected] A. T. Azar Misr University for Science & Technology (MUST), 6th of October City, Egypt A. E. Hassanien Chairman of Scientific Research Group in Egypt (SRGE), Cairo, Egypt e-mail: [email protected] S. E.-O. Hanafy Faculty of Computers and Information, Cairo University, Cairo, Egypt
V. Snášel et al. (eds.), Soft Computing in Industrial Applications, Advances in Intelligent Systems and Computing 223, DOI: 10.1007/978-3-319-00930-8_19, Springer International Publishing Switzerland 2014
209
210
A. S. A. Aziz et al.
1 Introduction With the evolution of computer networks during the past few years, security is a crucial issue and a basic demand for computer systems. Attacks are expanding and evolving as well, making it important to come up with new and advanced solutions for network security. Intrusion Detection Systems (IDS) have been around us for a some time, as an essential mechanism to protect computer systems, where they identify malicious activities that occur in that protected system. Genetic Algorithms (GA) are a group of computational models inspired by natural selection [1, 2]. This solution works on a group of chromosomes-like data structure (a population) where they reproduce new individuals that would be more be fitting in the environment. These new generations are developed using selection and recombination functions such as crossover and mutation [3]. The GAs were first seen as optimization solutions, but now they are applied in a variety of systems, including the IDSs [4, 5]. The GA is used as a machine learning technique to generate artificial intelligence detection rules. The rules are usually in the if-then forms, where the conditions are values that represent normal samples or values to indicate an intrusion is in the act [3, 6]. For a Network-based IDS (NIDS), usually the network traffic is used to build a model and detect anomalous network activities. Many features can be extracted and used in a GA to generate the rules, and these features may be of different data
Data Loading...
