Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Server-Side Machine Learning for Cheat Detection in Massively Multiplayer Online Role-Playing Games

, ,

DOI: http://dx.doi.org/10.15439/2026F1905

Citation: Konrad Operacz, ,

Full text

Abstract. Cheating in massively multiplayer online role-playing games (MMORPGs) degrades gameplay fairness and causes significant economic harm to game operators. Existing anti-cheat mechanisms predominantly operate on the client side, making them susceptible to bypass by modified clients or external automation tools. This paper presents the Cheat Detection System (CDS), a server-side machine learning framework developed as part of an industrial R\&D project and validated on a controlled MMORPG testbed. The CDS integrates three complementary algorithms: a one-class Support Vector Machine (SVM) for detecting temporally anomalous player actions, an Affinity Propagation clustering algorithm for identifying unnaturally regular bot movement patterns, and a multilayer perceptron (MLP) acting as a meta-level decision engine. A login anomaly module employs behavioral profiling to detect unauthorized account access. Experimental results demonstrate F-scores ranging from 0.81 to 1.00 across five cheat categories, with a CPU overhead of less than 0.02 percentage points when running alongside 100 concurrent players. The modular architecture allows straightforward extension to new cheat patterns without redeployment of the core system.

References

  1. Newzoo, “Global Games Market Report,” 2023. [Online]. Available: https://newzoo.com
  2. BattleEye Innovations, “BattleEye Anti-Cheat,” product documentation, 2023. [Online]. Available: https://www.battleye.com
  3. J. Tao, J. Xu, L. Gong, Y. Li, C. Fan, and Z. Zhao, “NGUARD: A game bot detection framework for NetEase MMORPGs,” in Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, pp. 811– 820, 2018. https://doi.org/10.1145/3219819.3219925
  4. J. Xu, Y. Luo, J. Tao, C. Fan, Z. Zhao, and J. Lu, “NGUARD+: An attention-based game bot detection framework via player behavior sequences,” ACM Trans. Knowl. Discov. Data, vol. 14, no. 6, pp. 1–24, 2020. https://doi.org/10.1145/3399711
  5. J. P. Pinto, A. Pimenta, and P. Novais, “Deep learning and multivariate time series for cheat detection in video games,” Mach. Learn., vol. 110, pp. 3037–3057, 2021. https://doi.org/10.1007/s10994-021-06055-x
  6. X. Qi, J. Pu, S. Zhao, R. Wu, and J. Tao, “BEAT: Behavior evaluation and anomaly tracking, game bot detection framework in RPG games,” in Proc. 6th Int. Conf. Algorithms, Computing and Artificial Intelligence (ACAI), 2023. https://doi.org/10.1145/3639631.3639683
  7. Y. Su, D. Yao, X. Chu, W. Li, J. Bi, S. Zhao, R. Wu, S. Zhang, J. Tao, and H. Deng, “Trajectory-based mobile game bots detection with Gaussian mixture model,” in Proc. Int. Conf. Artificial Neural Networks (ICANN), 2022. https://doi.org/10.1007/978-3-031-15934-3_38
  8. M. L. Han, B. I. Kwak and H. K. Kim, “Cheating and detection method in massively multiplayer online role-playing game: Systematic literature review,” IEEE Access, vol. 10, pp. 49038–49060, 2022. https://doi.org/ 10.1109/ACCESS.2022.3172110
  9. M. Chung, K. H. Yoo, J. Kim, and H. K. Kim, “Game bot detection approach based on behavior analysis and consideration of various play styles,” ETRI J., vol. 35, no. 6, pp. 1058–1067, 2013. https://doi.org/10. 4218/etrij.13.2013.0049
  10. H. Alayed, F. Frangoudes, and C. Neuman, “Behavioral-based cheating detection in online first person shooters using machine learning techniques,” in Proc. IEEE Conf. Computational Intelligence and Games (CIG), pp. 1–8, 2013. https://doi.org/10.1109/CIG.2013.6633617
  11. B. Schölkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson, “Estimating the support of a high-dimensional distribution,” Neural Comput., vol. 13, no. 7, pp. 1443–1471, 2001. https://doi.org/10.1162/089976601750264965
  12. Ye, N. and Chen, Q., “An anomaly detection technique based on a chisquare statistic for detecting intrusions into information systems,” Qual. Reliab. Eng. Int., vol. 17, no. 2, pp. 105–112, 2001. https://doi.org/10. 1002/qre.392
  13. B. J. Frey and D. Dueck, “Clustering by passing messages between data points,” Science, vol. 315, no. 5814, pp. 972–976, 2007. https: //doi.org/10.1126/science.1136800
  14. iMatix Corporation, “ZeroMQ: Distributed Messaging,” 2023. [Online]. Available: https://zeromq.org
  15. A. S. Ashoor and S. Gore, “Difference between Intrusion Detection System (IDS) and Intrusion Prevention System (IPS),” in Advances in Network Security and Applications (CNSA 2011), Communications in Computer and Information Science, vol. 196, Springer, Berlin, Heidelberg, 2011, pp. 497–501. https://doi.org/10.1007/978-3-642-22540-6_48
  16. E. Heijnen (Dark Byte), “Cheat Engine,” open-source memory scanner and debugger, 2019. [Online]. Available: https://www.cheatengine.org
  17. J. Woo and H. K. Kim, “Survey and research direction on online game security,” in Proc. Workshop at SIGGRAPH Asia (WASA 2012), Singapore, 2012, pp. 19–25. https://doi.org/10.1145/2425296.2425300