A novel approach for privacy preserving cheat detection in E-Sports using cloud-based computer vision techniques

Sharma, Kartikey (2023) A novel approach for privacy preserving cheat detection in E-Sports using cloud-based computer vision techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (4MB) | Preview

Abstract

The exponential growth of the e-sports industry has been shadowed by the rise of sophisticated cheating methods, posing significant threats to the integrity and fairness of competitive gaming. This research addresses the pressing need for effective, non-invasive cheat detection mechanisms by exploring the integration of cloud-based computer vision techniques. Specifically, it investigates using a fine-tuned YOLOv8 model in the cloud for real-time cheat detection in e-sports. The motivation behind this study is to establish a robust anti-cheat framework that balances stringent security measures with paramount concerns for user privacy, a balance often overlooked in conventional anti-cheat systems.

Our research involved developing a real-time object detection model trained on data from the open-source game AssaultCube. The model's performance was evaluated based on its accuracy, precision, recall, and processing speed, particularly in detecting cheats like Extra Sensory Perception (ESP) hacks. Significant findings include the model's high precision and recall rates for the classifications and its remarkable processing speed, achieving frame processing in less than 15 milliseconds on average when deployed on a GPU-enhanced cloud platform. This study not only demonstrates the feasibility of implementing AI-driven cheat detection in real-time but also opens new avenues for ethical and privacy-preserving approaches in gaming security.

The research aims to provide a groundbreaking perspective in the application of vision AI and cloud computing in cybersecurity, particularly in the domain of e-sports, setting the stage for more advanced, efficient, and ethically conscious anti-cheat systems in the future.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Salahuddin, Jawad UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security G Geography. Anthropology. Recreation > GV Recreation Leisure > Games and Amusements > Computer Games. Video Games.
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	25 Apr 2025 08:25
Last Modified:	25 Apr 2025 08:25
URI:	https://norma.ncirl.ie/id/eprint/7465

Actions (login required)

View Item