A Survey of Recent Advances in Artificial Intelligence for Detecting Balance-Breaking Behaviors in FPS Games

Jingchen Yang

doi:10.47297/taposatWSP2633-456917.20250609

PDF
Export
Share
Collection
Album

A Survey of Recent Advances in Artificial Intelligence for Detecting Balance-Breaking Behaviors in FPS Games

Volume 6, Issue 9

Views: 0 Downloads: 4

A Survey of Recent Advances in Artificial Intelligence for Detecting Balance-Breaking Behaviors in FPS Games
A Survey of Recent Advances in Artificial Intelligence for Detecting Balance-Breaking Behaviors in FPS Games
Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, 215000, China
Vol. 6, Issue 9, Pages: 85-89(2025)
Published：30 September 2025
DOI：10.47297/taposatWSP2633-456917.20250609
Accepted：

Scan QR Code

Yang Jingchen.A Survey of Recent Advances in Artificial Intelligence for Detecting Balance-Breaking Behaviors in FPS Games[J].Theory and Practice of Science and Technology,2025,06(09):85-89.
DOI：

Yang Jingchen.A Survey of Recent Advances in Artificial Intelligence for Detecting Balance-Breaking Behaviors in FPS Games[J].Theory and Practice of Science and Technology,2025,06(09):85-89. DOI： 10.47297/taposatWSP2633-456917.20250609.

摘要

Abstract

First-person shooter games have become a cornerstone of esports due to their competitiveness and commercial value. However

balance-breaking behaviors such as cheating and smurfing severely undermine fairness

degrade player experience

and threaten the sustainability of the industry. Traditional rule-based or manual inspection approaches have proven inadequate against the growing sophistication of such behaviors. In recent years

artificial intelligence

with its strengths in pattern recognition

temporal modeling

and anomaly detection

has emerged as a promising solution for both research and industrial applications. This paper reviews major advances in AI-driven detection of balance-breaking behaviors in FPS games over the past decade

covering methods based on behavioral features

input device dynamics

vision-based analysis

and unsupervised learning

while comparing their strengths and limitations in terms of accuracy

efficiency

and robustness. Finally

the paper identifies critical challenges—including data scarcity

adversarial dynamics

and the lack of explainability—and proposes future directions focusing on large-scale open dataset construction

adversarial and adaptive modeling

and the development of explainable AI frameworks.

关键词

Keywords

references

China Audio-Visual and Digital Publishing Association, E-sports Working Committee. 2024 China E-sports Industry Report - FX Report . n.d. https://www.fxbaogao.com/view?id=4629699 & requestId= & query=%7B%22keywords%22%3A%222024%E5%B9%B4%E4%B8%AD%E5%9B%BD%E7%94%B5%E5%AD%90%E7%AB%9E%E6%8A%80%E4%BA%A7%E4%B8%9A%E6%8A%A5%E5%91%8A%22%7D & index=0 & pid= & xid= (accessed June 24, 2025).

Collins S, Poulopoulos A, Muench M, Chothia T. Anti-Cheat: Attacks and the Effectiveness of Client-Side Defences. Proceedings of the 2024 Workshop on Research on offensive and defensive techniques in the context of Man At The End (MATE) attacks, Salt Lake City UT USA: ACM; 2024, p. 30 – 43 .

Choi M, Ko G, Cha SK. BotScreen: Trust Everybody, but Cut the Aimbots Yourself n.d.

VALORANT Systems Health Series - Smurf Detection 2022. https://playvalorant.com/en-us/news/dev/valorant-systems-health-series-smurf-detection/ (accessed June 24, 2025).

Alayed H, Frangoudes F, Neuman C. Behavioral-based cheating detection in online first person shooters using machine learning techniques. 2013 IEEE Conference on Computational Inteligence in Games (CIG), Niagara Falls, ON, Canada: IEEE; 2013, p. 1 – 8 .

Chen K-T, Pao H-KK, Chang H-C. Game bot identification based on manifold learning. Proceedings of the 7th ACM SIGCOMM Workshop on Network and System Support for Games, Worcester Massachusetts: ACM; 2008, p. 21 – 6 .

Liu D, Gao X, Zhang M, Wang H, Stavrou A. Detecting Passive Cheats in Online Games via Performance-Skillfulness Inconsistency. 2017 47th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), Denver, CO, USA: IEEE; 2017, p. 615 – 26 .

Yu S-Y, Hammerla N, Yan J, Andras P. Aimbot Detection in Online FPS Games Using a Heuristic Method Based on Distribution Comparison Matrix. In: Huang T, Zeng Z, Li C, Leung CS, editors. Neural Information Processing, vol. 7667 , Berlin, Heidelberg: Springer Berlin Heidelberg; 2012, p. 654 – 61 .

Jonnalagadda A, Frosio I, Schneider S, McGuire M, Kim J. Robust Vision-Based Cheat Detection in Competitive Gaming 2021.

Spijkerman R, Marie Ehlers E. Cheat Detection in a Multiplayer First-Person Shooter Using Artificial Intelligence Tools. Proceedings of the 2020 3rd International Conference on Computational Intelligence and Intelligent Systems, Tokyo Japan: ACM; 2020, p. 87 – 92 .

Buckley D, Chen K, Knowles J. Predicting skill from gameplay input to a first-person shooter. 2013 IEEE Conference on Computational Inteligence in Games (CIG), Niagara Falls, ON, Canada: IEEE; 2013, p. 1 – 8 .

Greige L. ANOMALY DETECTION IN COMPETITIVE MULTIPLAYER GAMES n.d.

McCauley B. An Auto-netnographic Approach to Understanding Alternate Gaming Accounts: How Smurfing Impacts the Prosumer Experience in Counter-Strike:Global Offensive 2023.

pmien996. The Hidden Crisis: How Smurfing is Undermining Competitive Integrity in Valorant. ReviewworldgameCom 2025. https://reviewworldgame.com/blog/news/the-hidden-crisis-how-smurfing-is-undermining-competitive-integrity-in-valorant/ (accessed June 24, 2025).

published NC. The ethics of smurfing. PC Gamer 2019.

Conroy E, Kowal M, Toth AJ, Campbell MJ. Boosting: Rank and skill deception in esports. Entertainment Computing 2021;36:100393.