100%(1)1 out of 1 people found this document helpful
This preview shows page 1 - 2 out of 24 pages.
informationArticleEffective Intrusion Detection System Using XGBoostSukhpreet Singh Dhaliwal *ID, Abdullah-Al NahidIDand Robert AbbasIDSchool of Engineering, Macquarie University, Sydney NSW 2109, Australia;[email protected] (A.-A.N.); [email protected] (R.A.)*Correspondence: [email protected]; Tel.: +61-2-9850-1558Received: 21 May 2018; Accepted: 19 June 2018; Published: 21 June 2018Abstract:As the world is on the verge of venturing into fifth-generation communication technologyand embracing concepts such as virtualization and cloudification, the most crucial aspect remains“security”, as more and more data get attached to the internet. This paper reflects a model designedto measure the various parameters of data in a network such as accuracy, precision, confusion matrix,and others. XGBoost is employed on the NSL-KDD (network socket layer-knowledge discovery indatabases) dataset to get the desired results. The whole motive is to learn about the integrity of dataand have a higher accuracy in the prediction of data. By doing so, the amount of mischievous datafloating in a network can be minimized, making the network a secure place to share information.The more secure a network is, the fewer situations where data is hacked or modified. By changingvarious parameters of the model, future research can be done to get the most out of the data enteringand leaving a network. The most important player in the network is data, and getting to know itmore closely and precisely is half the work done. Studying data in a network and analyzing thepattern and volume of data leads to the emergence of a solid Intrusion Detection System (IDS), thatkeeps the network healthy and a safe place to share confidential information.Keywords:classifiers; eXtreme Gradient Boosting (XGBoost); intrusion detection system (IDS);network socket layer-knowledge discovery in databases (NSL-KDD)1. IntroductionOne of the most important needs in life is security, whether in normal day-to-day life or in thecloud world. The year 2017 witnessed a series of ransomware attacks (a simple form of malware thatlocks down computer files using strong encryption, and then hackers ask for money in exchange forrelease of the compromised files), targets including San Francisco’s light-rail network, Britain’s NationalHealth Service, and even companies such as FedEx. One example is the WannaCry Ransomware Attackwhich compromised thousands of computers, and lately companies such as Amazon, Google, and IBMhave started hiring the best minds in digital security so that their establishments across the world do notget easily compromised. Moreover, one can ask Amazon, Twitter, Netflix, and others about the Denialof Service attacks their servers faced back in 2016 , in which the attackers flooded the system withuseless packets, making the system unavailable. There were virtual machine escape attacks reportedback in 2008 by Core Security Technologies, in which a vulnerability (CVE-20080923) was found inVMware’s (software developing firm named VMware Inc., Palo Alto, CA, USA) mechanism of shared