Abstract— Inrecent years there is a growing number of attacks in the computer networks.Therefore, the use of a prevention mechanism is an inevitable need for securityadmins. Although firewalls are preferred as the first layer of protection, itis not sufficient for preventing lots of the attacks, especially from theinsider attacks. Intrusion Detection Systems (IDSs) have emerged as aneffective solution to these types of attacks. For increasing the efficiency of theIDS system, a dynamic solution, which can adapt itself and can detect new typesof intrusions with a dynamic structure by the use of learning algorithms is mostlypreferred. In previous years, some machine learning approaches are implementedin lots of IDSs. In the current position of artificial intelligence, most ofthe learning systems are transferred with the use of Deep Learning approachesdue to its flexibility and the use of Big Data with high accuracy. In thispaper, we propose a clustered approach to detect the intrusions in a network.Firstly, the system is trained with Deep Neural Network on a Big Data set byaccelerating its performance with the use of CUDA architecture. Experimentalresults show that the proposed system has a very good accuracy rate and lowruntime duration with the use of this parallel computation architecture. Additionally,the proposed system needs a relatively small duration for training the system