A deep-learning approach to game bot identification via behavioural features analysis in complex massively-cooperative environments. (31st March 2023)

• Record Type: Journal Article
• Authors: Cuzzocrea, Alfredo; Martinelli, Fabio; Mercaldo, Francesco
• Is Part Of: International journal of data mining, modelling and management. Volume 15:Number 1(2023)
• Page Start: 1
• Page End: 29
• Publication Date: 2023-03-31
• Subjects: game bot detection -- complex massively-cooperative environments -- machine learning -- deep learning -- massively multiplayer online role-playing games -- MMORPGs; Data mining -- Periodicals; Information science -- Periodicals; Databases -- Periodicals; 005.7
• Languages: English
• ISSNs: 1759-1163

Abstract

In the so-called massively multiplayer online role-playing games (MMORPGs), malicious players have the possibility of obtaining some kind of gains from competitions, via easy victories achieved thanks to the introduction of game bots in the games. In order to maintain fairness among players, it is important to detect the presence of game bots during video games so that they can be expelled from the games. This paper describes an approach to distinguish human players from game bots based on behavioural analysis. This implemented via supervised machine learning (ML) and deep learning (DL) algorithms. In order to detect game bots, considered algorithms are first trained with labelled features and then used to classify unseen-before features. In this paper, the performance of our game bots detection approach is experimentally obtained. The dataset we use for training and classification is extracted from logs generated during online video games matches of a real-life MMORPG.