Companies outsource a lot of their development tasks. The use of external development teams introduces security problems which may lead to data breaches and even corporate espionage where business ideas are used in other companies, leading to leaking of trade secrets. A detailed explanation of the security implications of outsourcing is given, with ways to mitigate such risks in the first section of the report. The report also explains some basics theory in cyber security such as information gathering, vulnerability scanning, exploitation and post exploitation. We also look at some software tools used in the field. Due to the lack of knowledge and awareness about cyber security, most small companies do not have enough protection against these malicious attacks. The proposed intrusion detection system is capable of recognizing various kinds of cyber attacks including denial of serviceattack, spoofing attack, sniffing attack and so on. The proposed system employs ensemble learning and feature selection techniques to reduce the computational cost and improve the detection rate simultaneously. This paper presents an intelligent intrusion detection system based on tree-structure machine learning models. After the implementation of the proposed intrusion detection system on standard data sets, the system has achieved high detection rate and low computational cost simultaneously. The method used to bring results is python with scikit library that can help with machine learning. The results will show figures of heatmap and scores of models that will explain how likely it will identify a cyber attack.