According to growing ICT and human dependence on it, maintaining availability, integrity and confidentiality of information is so critical. So in this context we must protect data and networks from attacks and illegal influences. Therefore intrusion detection systems have become one of the most important issues and investigations to improve its ability, speed and flexibility in the face of Zero day's cyber-attacks. In this paper, after introducing the computer network attacks and going over the genetic algorithm, a model will be presented based on the genetic algorithm and by using inheritance features to detect the Zero day intrusions or converted types of the existing attacks(infiltration ways), and implemented it on WEKA software. Finally examine the relevant index of proposed model.