AntiCheatPT: A Transformer-Based Approach to Cheat Detection in Competitive Computer Games

Mille Mei Zhen Loo; Gert Lužkov; Paolo Burelli

doi:10.48550/arXiv.2508.06348

AntiCheatPT: A Transformer-Based Approach to Cheat Detection in Competitive Computer Games

Mille Mei Zhen Loo
, Gert Lužkov
, Paolo Burelli

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

Cheating in online video games compromises the integrity of gaming experiences. Anti-cheat systems, such as VAC (Valve Anti-Cheat), face significant challenges in keeping pace with evolving cheating methods without imposing invasive measures on users' systems. This paper presents AntiCheatPT_256, a transformer-based machine learning model designed to detect cheating behaviour in Counter-Strike 2 using gameplay data. To support this, we introduce and publicly release CS2CD: A labelled dataset of 795 matches. Using this dataset, 90,707 context windows were created and subsequently augmented to address class imbalance. The transformer model, trained on these windows, achieved an accuracy of 89.17% and an AUC of 93.36% on an unaugmented test set. This approach emphasizes reproducibility and real-world applicability, offering a robust baseline for future research in data-driven cheat detection.

Original language	English
Title of host publication	2025 IEEE Conference on Games
Publisher	IEEE
Publication date	2025
DOIs	https://doi.org/10.48550/arXiv.2508.06348 https://doi.org/10.1109/CoG64752.2025.11114092
Publication status	Published - 2025
Event	Games - Instituto Superior Tecnico, Lisbon, Portugal Duration: 26 Aug 2025 → 29 Aug 2025 Conference number: 7 https://cog2025.inesc-id.pt/

Conference

Conference	Games
Number	7
Location	Instituto Superior Tecnico
Country/Territory	Portugal
City	Lisbon
Period	26/08/2025 → 29/08/2025
Internet address	https://cog2025.inesc-id.pt/

Keywords

Cheat detection
Transformer-based model
Counter-Strike 2
Machine learning
Gameplay data

Access to Document

CS2CD.Counter-Strike_2_Cheat_Detection
Loo, M. M. Z. (Creator), Lužkov, G. (Creator) & Burelli, P. (Supervisor), Hugging Face, 2025
DOI: 10.57967/hf/5315, https://huggingface.co/datasets/CS2CD/CS2CD.Counter-Strike_2_Cheat_Detection
Dataset: Software

Cite this

@inproceedings{536776026db848afb52d9b370e77c11d,

title = "AntiCheatPT: A Transformer-Based Approach to Cheat Detection in Competitive Computer Games",

abstract = "Cheating in online video games compromises the integrity of gaming experiences. Anti-cheat systems, such as VAC (Valve Anti-Cheat), face significant challenges in keeping pace with evolving cheating methods without imposing invasive measures on users' systems. This paper presents AntiCheatPT\_256, a transformer-based machine learning model designed to detect cheating behaviour in Counter-Strike 2 using gameplay data. To support this, we introduce and publicly release CS2CD: A labelled dataset of 795 matches. Using this dataset, 90,707 context windows were created and subsequently augmented to address class imbalance. The transformer model, trained on these windows, achieved an accuracy of 89.17\% and an AUC of 93.36\% on an unaugmented test set. This approach emphasizes reproducibility and real-world applicability, offering a robust baseline for future research in data-driven cheat detection.",

keywords = "Cheat detection, Transformer-based model, Counter-Strike 2, Machine learning, Gameplay data",

author = "Loo, \{Mille Mei Zhen\} and Gert Lu{\v z}kov and Paolo Burelli",

year = "2025",

doi = "10.48550/arXiv.2508.06348",

language = "English",

booktitle = "2025 IEEE Conference on Games",

publisher = "IEEE",

address = "United States",

note = "Games , IEEE CoG ; Conference date: 26-08-2025 Through 29-08-2025",

url = "https://cog2025.inesc-id.pt/",

}

TY - GEN

T1 - AntiCheatPT: A Transformer-Based Approach to Cheat Detection in Competitive Computer Games

AU - Loo, Mille Mei Zhen

AU - Lužkov, Gert

AU - Burelli, Paolo

N1 - Conference code: 7

PY - 2025

Y1 - 2025

N2 - Cheating in online video games compromises the integrity of gaming experiences. Anti-cheat systems, such as VAC (Valve Anti-Cheat), face significant challenges in keeping pace with evolving cheating methods without imposing invasive measures on users' systems. This paper presents AntiCheatPT_256, a transformer-based machine learning model designed to detect cheating behaviour in Counter-Strike 2 using gameplay data. To support this, we introduce and publicly release CS2CD: A labelled dataset of 795 matches. Using this dataset, 90,707 context windows were created and subsequently augmented to address class imbalance. The transformer model, trained on these windows, achieved an accuracy of 89.17% and an AUC of 93.36% on an unaugmented test set. This approach emphasizes reproducibility and real-world applicability, offering a robust baseline for future research in data-driven cheat detection.

AB - Cheating in online video games compromises the integrity of gaming experiences. Anti-cheat systems, such as VAC (Valve Anti-Cheat), face significant challenges in keeping pace with evolving cheating methods without imposing invasive measures on users' systems. This paper presents AntiCheatPT_256, a transformer-based machine learning model designed to detect cheating behaviour in Counter-Strike 2 using gameplay data. To support this, we introduce and publicly release CS2CD: A labelled dataset of 795 matches. Using this dataset, 90,707 context windows were created and subsequently augmented to address class imbalance. The transformer model, trained on these windows, achieved an accuracy of 89.17% and an AUC of 93.36% on an unaugmented test set. This approach emphasizes reproducibility and real-world applicability, offering a robust baseline for future research in data-driven cheat detection.

KW - Cheat detection

KW - Transformer-based model

KW - Counter-Strike 2

KW - Machine learning

KW - Gameplay data

U2 - 10.48550/arXiv.2508.06348

DO - 10.48550/arXiv.2508.06348

M3 - Article in proceedings

BT - 2025 IEEE Conference on Games

PB - IEEE

T2 - Games

Y2 - 26 August 2025 through 29 August 2025

ER -

AntiCheatPT: A Transformer-Based Approach to Cheat Detection in Competitive Computer Games

Abstract

Conference

Keywords

Access to Document

Fingerprint

Datasets

CS2CD.Counter-Strike_2_Cheat_Detection

Cite this