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

Daniele Spina;Andrea Bottino;Leonardo Chiariglione;Marco Mazzaglia;Francesco Strada
In corso di stampa

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.
In corso di stampa
File in questo prodotto:
File Dimensione Formato  
IEEE_GEM___MPAI_SPG.pdf

non disponibili

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 905.42 kB
Formato Adobe PDF
905.42 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

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/11583/2987584