Litcius/Paper detail

Botnet Attack Detection using Machine Learning

Mustafa Alshamkhany, Wisam Alshamkhany, Mohamed Mansour, Mueez Khan, Salam Dhou, Fadi Aloul

202091 citationsDOI

Abstract

With the advancement of computers and technology, security threats are also evolving at a fast pace. Botnets are one such security threat which requires a high level of research and focus in order to be eliminated. In this paper, we use machine learning to detect Botnet attacks. Using the Bot-IoT and University of New South Wales (UNSW) datasets, four machine learning models based on four classifiers are built: Naïve Bayes, K-Nearest Neighbor, Support Vector Machine, and Decision Trees. Using 82,000 records from UNSW-NB15 dataset, the decision trees model has yielded the best overall results with 99.89% testing accuracy, 100% precision, 100% recall, and 100% F-score in detecting botnet attacks.

Topics & Concepts

BotnetComputer scienceNaive Bayes classifierMachine learningDecision treeArtificial intelligenceSupport vector machinePaceComputer securityPrecision and recallRandom forestFocus (optics)The InternetWorld Wide WebGeographyPhysicsOpticsGeodesyNetwork Security and Intrusion DetectionAdvanced Malware Detection TechniquesInternet Traffic Analysis and Secure E-voting