This work introduces MPAI-SPG, a novel approach to mitigate latency and detect cheating in online gaming through server-based prediction. The paper reports the implementation of this approach in an online racing game. Using machine learning, we developed a prediction module trained on a custom-built dataset, which is publicly available. Experimental sessions with real players were conducted to assess prediction accuracy and the overall solution's effectiveness in ensuring smooth multiplayer gaming despite data absence. The results demonstrate MPAI-SPG's potential to enhance the gaming experience amidst network challenges. The approach allows for continuous improvement in prediction accuracy, leveraging new training techniques.

AI Server-Side Prediction for Latency Mitigation and Cheating Detection: The MPAI-SPG Approach

Bottino, Andrea;Cavagnino, Davide;Lucenteforte, Maurizio;Mazzaglia, Marco;
2024-01-01

Abstract

This work introduces MPAI-SPG, a novel approach to mitigate latency and detect cheating in online gaming through server-based prediction. The paper reports the implementation of this approach in an online racing game. Using machine learning, we developed a prediction module trained on a custom-built dataset, which is publicly available. Experimental sessions with real players were conducted to assess prediction accuracy and the overall solution's effectiveness in ensuring smooth multiplayer gaming despite data absence. The results demonstrate MPAI-SPG's potential to enhance the gaming experience amidst network challenges. The approach allows for continuous improvement in prediction accuracy, leveraging new training techniques.
2024
IEEE CTSoc Gaming, Entertainment and Media
Torino, Italy
5-7 giugno 2024
2024 IEEE Gaming, Entertainment, and Media Conference (GEM)
IEEE
474
479
979-8-3503-7453-7
979-8-3503-7454-4
https://ieeexplore.ieee.org/document/10585519
cheating; latency; machine learning; online multiplayer gaming;
Spina, Daniele; Bottino, Andrea; Cavagnino, Davide; Chiariglione, Leonardo; Lucenteforte, Maurizio; Mazzaglia, Marco; Strada, Francesco
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/2000390
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact