Intrusion Detection Model Based On Particle Swarm Optimization and Support Vector Machine

Advance in information and communication technologies, force us to keep most of the information electronically, consequently, the security of information has become a fundamental issue. The traditional intrusion detection systems look for unusual or suspicious activity, such as patterns of network traffic that are likely indicators of unauthorized activity. However, normal operation often produces traffic that matches likely "attack signature", resulting in false alarms. One main drawback is the inability of detecting new attacks which do not have known signatures. In this paper particle swarm optimization (PSO) is used to implement a feature selection, and support vector machine (SVMs) with the one-versus-rest method serve as a fitness function of PSO for classification problems from the literature. Experimental result shows that our method allows us to recognize not only known attacks but also to detect suspicious activity that may be the result of a new, unknown attack. Our method simplifies features effectively and obtains a higher classification accuracy compared to other methods