Tools
Tools
Karkera, Sachet (2023) Anomaly Detection for Identifying Cheating Behaviours and Techniques in Online Gaming Using AI. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Gaming has been gaining popularity since it has become mainstream and has become one of the largest sectors in terms of money, investment, and involvement. By hacking into the game's mechanics to alter the results of a particular match to their liking, some players may turn to illicit and immoral strategies to improve their performance. Cheats such as aimbots, wallhacks, and bots playing or impersonating as real players have been a threat to the gaming community. This compromises fair play and discourages people with no experience from attempting to become competent in a particular game. Employing a visual object detection algorithm, this research attempts to evaluate current cheat detection strategies while putting new methodologies for identifying Aim Bot, Wallhack, and Speedhacks in online gaming. Aim Bot detection includes statistical analysis and dynamic thresholding techniques to identify and flag instances of aim bot usage. Wallhack and Object detection utilises YOLOv8, an innovative algorithm, enabling real-time identification of wallhack usage. Speedhack detection incorporates tick rate analysis and pattern recognition to detect and flag instances of speedhack usage. This research intends to eliminate cheating methods while protecting the player’s privacy settings and their system while upholding the integrity of the online gaming community by using machine learning and artificial intelligence.
Actions (login required)
 |
View Item |