pith. machine review for the scientific record. sign in

arxiv: 2605.10867 · v1 · submitted 2026-05-11 · 💻 cs.CR · cs.AI· cs.CV· cs.LG· cs.NI

Recognition: no theorem link

BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data

Ishpuneet Singh , Gursmeep Kaur , Uday Pratap Singh Atwal , Guramrit Singh , Gurjot Singh , Maninder Singh
Authors on Pith no claims yet

Pith reviewed 2026-05-12 03:37 UTC · model grok-4.3

classification 💻 cs.CR cs.AIcs.CVcs.LGcs.NI
keywords behavioral biometricscontinuous authenticationmultimodal datasetesportsgameplay datamouse dynamicskeystroke eventsuser profiling
0
0 comments X

The pith

The BEACON dataset supplies over 100 hours of synchronized multimodal data from Valorant gameplay to support research on behavioral biometrics for continuous authentication.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a new dataset called BEACON collected from competitive Valorant matches. It records multiple streams of information including precise mouse movements, key presses, network traffic, video of the screen, and hardware details from 28 different players over 79 sessions. This amounts to roughly 430 gigabytes and more than 102 hours of play. The goal is to give researchers a realistic testbed for developing systems that can continuously verify users based on how they play games, which involves demanding motor skills and quick thinking. If successful, such datasets could improve security in digital environments where traditional passwords fall short.

Core claim

BEACON is a multimodal dataset comprising approximately 430 GB of synchronized data from 79 sessions across 28 distinct players, totaling an estimated 102.51 hours of active Valorant gameplay. It includes high-frequency mouse dynamics, keystroke events, network packet captures, screen recordings, hardware metadata, and in-game configuration context. The dataset is designed to serve as a rigorous stress test for behavioral biometrics due to the high precision motor skills and cognitive load inherent to tactical shooters, enabling studies in continuous authentication, behavioral profiling, user drift, and multimodal representation learning.

What carries the argument

The synchronized collection of high-frequency behavioral signals from competitive esports gameplay, which provides the multimodal context for learning user-specific fingerprints.

If this is right

  • The dataset enables the study of continuous authentication using gameplay behavior under realistic conditions.
  • It facilitates research on how behavioral patterns may drift over time in high-stakes settings.
  • Researchers can explore multimodal fusion techniques for more robust user identification.
  • It creates a benchmark for evaluating security models in an esports environment with diverse player skill levels.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This approach might extend to other domains requiring fine motor control and decision-making, such as professional software development or vehicle operation.
  • If models from this data generalize well, they could be adapted for real-time monitoring in online gaming platforms to detect account sharing or unauthorized access.
  • The emphasis on synchronized modalities could encourage similar collection efforts in non-gaming high-cognitive-load tasks to test biometric robustness.

Load-bearing premise

That the specific demands of Valorant gameplay provide a sufficiently demanding and representative test for the effectiveness of behavioral biometrics derived from these modalities.

What would settle it

If authentication models built using BEACON data perform no better than those from smaller or unimodal datasets when tested on new sessions or different players, the value of this large-scale multimodal collection would be called into question.

Figures

Figures reproduced from arXiv: 2605.10867 by Guramrit Singh, Gurjot Singh, Gursmeep Kaur, Ishpuneet Singh, Maninder Singh, Uday Pratap Singh Atwal.

Figure 1
Figure 1. Figure 1: Architecture of the custom BEACON logger [ [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Log-scale distribution of the overall event and packet counts across the primary modalities, [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Aggregate heatmaps illustrating the spatial distribution of sensorimotor interactions across [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Cross-modality behavioral comparison. The Z-score heatmap standardises median features [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Inter-user separability analysis. The distribution of sensorimotor features for a single [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: The secure data pipeline and upload portal, illustrating local caching, chunked HTTPS [PITH_FULL_IMAGE:figures/full_fig_p015_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Statistical distribution of Keyboard dynamics across all 28 participants. Notice the high [PITH_FULL_IMAGE:figures/full_fig_p016_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Statistical distribution of Mouse dynamics across all 28 participants. Features such as Event [PITH_FULL_IMAGE:figures/full_fig_p017_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Statistical distribution of Network telemetry across all 28 participants. The integration of [PITH_FULL_IMAGE:figures/full_fig_p018_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Detailed Performance Metrics for Unimodal Mouse Dynamics. [PITH_FULL_IMAGE:figures/full_fig_p023_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Detailed Performance Metrics for Unimodal Keyboard Dynamics. [PITH_FULL_IMAGE:figures/full_fig_p024_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Detailed Performance Metrics for Multi-modal Early Fusion (Combined Profile). [PITH_FULL_IMAGE:figures/full_fig_p025_12.png] view at source ↗
read the original abstract

Continuous authentication in high-stakes digital environments requires datasets with fine-grained behavioral signals under realistic cognitive and motor demands. But current benchmarks are often limited by small scale, unimodal sensing or lack of synchronised environmental context. To address this gap, this paper introduces BEACON ( Behavioral Engine for Authentication \& Continuous Monitoring), a large-scale multimodal dataset that captures diverse skill tiers in competitive \textit{Valorant} gameplay. BEACON contains approximately 430 GB of synchronised modality data (461 GB total on-disk including auxiliary \textit{Valorant} configuration captures) from 79 sessions across 28 distinct players, estimated at 102.51 hours of active gameplay, including high-frequency mouse dynamics, keystroke events, network packet captures, screen recordings, hardware metadata, and in-game configuration context. BEACON leverages the high precision motor skills and high cognitive load that are inherent to tactical shooters, making it a rigorous stress test for the robustness of behavioral biometrics. The dataset allows for the study of continuous authentication, behavioral profiling, user drift and multimodal representation learning in a high-fidelity esports setting. The authors release the dataset and code on Hugging Face and GitHub to create a reproducible benchmark for evaluating next-generation behavioral fingerprinting and security models

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript introduces BEACON, a multimodal dataset collected from 79 sessions of competitive Valorant gameplay involving 28 distinct players. It reports approximately 430 GB of synchronized data (461 GB on-disk) spanning 102.51 hours, encompassing high-frequency mouse dynamics, keystroke events, network packet captures, screen recordings, hardware metadata, and in-game configuration context. The dataset is positioned as a rigorous stress test for behavioral biometrics due to the high motor precision and cognitive load of tactical shooters, enabling research on continuous authentication, behavioral profiling, user drift, and multimodal representation learning. The authors release the data and associated code on Hugging Face and GitHub.

Significance. If the synchronization accuracy, data quality, and collection protocols are rigorously validated and documented, BEACON could serve as a valuable large-scale benchmark for behavioral fingerprinting and security research. It addresses limitations in existing datasets by providing synchronized multimodal streams under realistic high-stakes conditions, potentially advancing continuous authentication systems and multimodal learning models. The public release supports reproducibility and community benchmarking.

major comments (1)
  1. Abstract and Data Collection section: The central claim that BEACON supplies 'synchronised modality data' suitable for multimodal representation learning and continuous authentication is load-bearing, yet the manuscript provides no quantitative validation. There are no reported details on the synchronization protocol, measured inter-modality latency or jitter, maximum temporal offsets (e.g., between mouse events and video frames), or validation metrics such as cross-modal alignment error bounds. Without these, the assumption that the streams are sufficiently aligned for downstream analyses cannot be assessed.
minor comments (2)
  1. Abstract: The active gameplay duration is stated as 'estimated at 102.51 hours'; provide the exact method of estimation and any exclusion criteria for inactive periods in the methods or dataset description section.
  2. Abstract: Clarify whether the 28 players are distinct across all 79 sessions or if some players contributed multiple sessions, and report any per-player session distribution to support claims of diversity.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive review and for identifying the need for greater transparency on synchronization. We address the major comment below and will revise the manuscript to incorporate additional details.

read point-by-point responses

  1. Referee: [—] Abstract and Data Collection section: The central claim that BEACON supplies 'synchronised modality data' suitable for multimodal representation learning and continuous authentication is load-bearing, yet the manuscript provides no quantitative validation. There are no reported details on the synchronization protocol, measured inter-modality latency or jitter, maximum temporal offsets (e.g., between mouse events and video frames), or validation metrics such as cross-modal alignment error bounds. Without these, the assumption that the streams are sufficiently aligned for downstream analyses cannot be assessed.

    Authors: We acknowledge that the current manuscript does not include quantitative validation of inter-modality alignment or a detailed description of the synchronization protocol. Data streams were captured with native high-resolution timestamps (mouse/keyboard events via low-level input hooks, network packets via libpcap, video frames via recording metadata) and aligned post hoc to a shared system clock started at the beginning of each session. However, explicit measurements of latency, jitter, or alignment error bounds are absent. In the revised manuscript we will add a dedicated subsection to the Data Collection section that (i) fully specifies the synchronization protocol and hardware/software configuration, (ii) reports any empirical offset measurements obtainable from the collection logs, and (iii) provides conservative error bounds derived from device sampling rates and known capture latencies. This addition will allow readers to evaluate the dataset's suitability for multimodal and continuous-authentication tasks. revision: yes

Circularity Check

0 steps flagged

Dataset release with no derivations, predictions or fitted parameters

full rationale

The manuscript is a dataset paper whose sole contribution is the description and release of BEACON (approximately 430 GB of synchronized multimodal Valorant gameplay recordings). It contains no equations, no claimed predictions, no parameter fitting, and no derivation chain. The abstract and full text limit themselves to data-collection details, modality lists, and release statements; none of these steps reduce to self-definition, self-citation load-bearing, or renaming of prior results. External verifiability is provided by the public Hugging Face/GitHub release, satisfying the criterion for a self-contained, non-circular contribution.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper's contribution is the creation and public release of the dataset itself. It relies on a domain assumption about the suitability of Valorant for behavioral biometrics testing but introduces no free parameters, new entities, or additional axioms beyond standard data-collection practices.

axioms (1)
  • domain assumption Valorant gameplay involves high precision motor skills and high cognitive load that make it a rigorous stress test for behavioral biometrics
    Invoked in the abstract to justify the dataset's value for continuous authentication research.

pith-pipeline@v0.9.0 · 5554 in / 1404 out tokens · 50016 ms · 2026-05-12T03:37:36.088528+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

39 extracted references · 39 canonical work pages

  1. [1]

    Integrating big data analytics and behavioral biometrics for advanced fraud detection.Sakarya University Journal of Computer and Information Sciences, 9(1):8–20, 2026

    Ahmed Abbas, Tareq Abed Mohammed, Zena Ez Dallalbash, and Adil Khalil. Integrating big data analytics and behavioral biometrics for advanced fraud detection.Sakarya University Journal of Computer and Information Sciences, 9(1):8–20, 2026. doi: 10.35377/saucis... 1729803. URLhttps://izlik.org/JA55RG93DW

    work page doi:10.35377/saucis 2026

  2. [2]

    Sapimouse: Mouse dynamics-based user authentication using deep feature learning

    Margit Antal, Norbert Fejér, and Krisztian Buza. Sapimouse: Mouse dynamics-based user authentication using deep feature learning. In2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI), pages 61–66, 2021. doi: 10.1109/SACI51354.2021.9465583

    work page doi:10.1109/saci51354.2021.9465583 2021

  3. [3]

    Realistic website fingerprinting by augmenting network traces

    Alireza Bahramali, Ardavan Bozorgi, and Amir Houmansadr. Realistic website fingerprinting by augmenting network traces. InProceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, CCS ’23, page 1035–1049, New York, NY , USA, 2023. Association for Computing Machinery. ISBN 9798400700507. doi: 10.1145/3576915.3616639. URLhttps:/...

    work page doi:10.1145/3576915.3616639 2023

  4. [4]

    Var-cnn and dynaflow: Improved attacks and defenses for website fingerprinting.CoRR, abs/1802.10215, 2018

    Sanjit Bhat, David Lu, Albert Kwon, and Srinivas Devadas. Var-cnn and dynaflow: Improved attacks and defenses for website fingerprinting.CoRR, abs/1802.10215, 2018. URL http: //arxiv.org/abs/1802.10215

    work page arXiv 2018

  5. [5]

    Sc2egset: Starcraft ii esport replay and game-state dataset.Scientific Data, 10(1):600, Sep 2023

    Andrzej Białecki, Natalia Jakubowska, Paweł Dobrowolski, Piotr Białecki, Leszek Krupi´nski, Andrzej Szczap, Robert Białecki, and Jan Gajewski. Sc2egset: Starcraft ii esport replay and game-state dataset.Scientific Data, 10(1):600, Sep 2023. ISSN 2052-4463. doi: 10.1038/ s41597-023-02510-7. URLhttps://doi.org/10.1038/s41597-023-02510-7

    work page doi:10.1038/s41597-023-02510-7 2023

  6. [6]

    Rapid skill capture in a first-person shooter

    David Buckley, Ke Chen, and Joshua Knowles. Rapid skill capture in a first-person shooter. IEEE Transactions on Computational Intelligence and AI in Games, 9(1):63–75, 2017. doi: 10.1109/TCIAIG.2015.2494849

    work page doi:10.1109/tciaig.2015.2494849 2017

  7. [7]

    User identification based on game-play activity patterns

    Kuan-Ta Chen and Li-Wen Hong. User identification based on game-play activity patterns. In Proceedings of the 6th ACM SIGCOMM Workshop on Network and System Support for Games, NetGames ’07, page 7–12, New York, NY , USA, 2007. Association for Computing Machinery. ISBN 9780980446005. doi: 10.1145/1326257.1326259. URL https://doi.org/10.1145/ 1326257.1326259

    work page doi:10.1145/1326257.1326259 2007

  8. [8]

    From clicks to security: Investigating continuous authentication via mouse dynamics, 2024

    Rushit Dave, Marcho Handoko, Ali Rashid, and Cole Schoenbauer. From clicks to security: Investigating continuous authentication via mouse dynamics, 2024. URL https://arxiv. org/abs/2403.03828

    work page arXiv 2024

  9. [9]

    Toward robust multi-tab website fingerprinting.IEEE Transactions on Networking, 34: 3656–3671, 2026

    Xinhao Deng, Xiyuan Zhao, Qilei Yin, Zhuotao Liu, Qi Li, Mingwei Xu, Ke Xu, and Jianping Wu. Toward robust multi-tab website fingerprinting.IEEE Transactions on Networking, 34: 3656–3671, 2026. doi: 10.1109/TON.2026.3666721

    work page doi:10.1109/ton.2026.3666721 2026

  10. [10]

    Keyrecs: A keystroke dynamics and typing pattern recognition dataset.Data in Brief, 50:109509, 2023

    Tiago Dias, João Vitorino, Eva Maia, Orlando Sousa, and Isabel Praça. Keyrecs: A keystroke dynamics and typing pattern recognition dataset.Data in Brief, 50:109509, 2023. ISSN 2352-

    work page 2023

  11. [11]

    URL https://www.sciencedirect

    doi: https://doi.org/10.1016/j.dib.2023.109509. URL https://www.sciencedirect. com/science/article/pii/S2352340923006091

    work page doi:10.1016/j.dib.2023.109509 2023

  12. [12]

    Your device may know you better than you know yourself – continuous authenti- cation on novel dataset using machine learning, 2024

    Pedro Gomes do Nascimento, Pidge Witiak, Tucker MacCallum, Zachary Winterfeldt, and Rushit Dave. Your device may know you better than you know yourself – continuous authenti- cation on novel dataset using machine learning, 2024. URL https://arxiv.org/abs/2403. 03832

    work page 2024

  13. [13]

    Amucs: Affective multimodal counter-strike video game dataset.Scientific Data, 12(1):1325, Jul 2025

    Marios Fanourakis and Guillaume Chanel. Amucs: Affective multimodal counter-strike video game dataset.Scientific Data, 12(1):1325, Jul 2025. ISSN 2052-4463. doi: 10.1038/s41597-025-05596-3. URLhttps://doi.org/10.1038/s41597-025-05596-3

    work page doi:10.1038/s41597-025-05596-3 2025

  14. [14]

    Fulop, L

    A. Fulop, L. Kovacs, T. Kurics, and E. Windhager-Pokol. Balabit mouse dynamics challenge data set. https://github.com/balabit/Mouse-Dynamics-Challenge, 2016. Accessed: 2026-05-07. 11

    work page 2016

  15. [15]

    Martin, Marta Beltrán, Alberto Fernández-Isabel, and Isaac Martín de Diego

    Alejandro G. Martin, Marta Beltrán, Alberto Fernández-Isabel, and Isaac Martín de Diego. Keystroke and mouse dynamics for ueba dataset, 2020. URL https://doi.org/10.17632/ f78jsh6zp9.2

    work page 2020

  16. [16]

    Calot, Jorge S

    Nahuel González, Enrique P. Calot, Jorge S. Ierache, and Waldo Hasperué. Towards liveness detection in keystroke dynamics: Revealing synthetic forgeries.Systems and Soft Computing, 4:200037, 2022. ISSN 2772-9419. doi: https://doi.org/10.1016/j.sasc.2022.200037. URL https://www.sciencedirect.com/science/article/pii/S2772941922000047

    work page doi:10.1016/j.sasc.2022.200037 2022

  17. [17]

    Bapm: Block attention profiling model for multi-tab website fingerprinting attacks on tor

    Zhong Guan, Gang Xiong, Gaopeng Gou, Zhen Li, Mingxin Cui, and Chang Liu. Bapm: Block attention profiling model for multi-tab website fingerprinting attacks on tor. InProceedings of the 37th Annual Computer Security Applications Conference, ACSAC ’21, page 248–259, New York, NY , USA, 2021. Association for Computing Machinery. ISBN 9781450385794. doi: 10....

    work page doi:10.1145/3485832.3485891 2021

  18. [18]

    Transformer-based model for multi- tab website fingerprinting attack

    Zhaoxin Jin, Tianbo Lu, Shuang Luo, and Jiaze Shang. Transformer-based model for multi- tab website fingerprinting attack. InProceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, CCS ’23, page 1050–1064, New York, NY , USA, 2023. Association for Computing Machinery. ISBN 9798400700507. doi: 10.1145/3576915.3623107. URLhttp...

    work page doi:10.1145/3576915.3623107 2023

  19. [19]

    Killourhy and Roy A

    Kevin S. Killourhy and Roy A. Maxion. Comparing anomaly-detection algorithms for keystroke dynamics. In2009 IEEE/IFIP International Conference on Dependable Systems & Networks, pages 125–134, 2009. doi: 10.1109/DSN.2009.5270346

    work page doi:10.1109/dsn.2009.5270346 2009

  20. [20]

    Learning models of individual behavior in chess

    Reid McIlroy-Young, Russell Wang, Siddhartha Sen, Jon Kleinberg, and Ashton Anderson. Learning models of individual behavior in chess. InProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’22, page 1253–1263. ACM, Au- gust 2022. doi: 10.1145/3534678.3539367. URL http://dx.doi.org/10.1145/3534678. 3539367

    work page doi:10.1145/3534678.3539367 2022

  21. [21]

    Charles Murphy and Charles C. Tappert. Clarkson university keystroke dataset II. Clarkson University CITeR, 2017. URL https://citer.clarkson.edu/ clarkson-university-keystroke-dataset-ii/

    work page 2017

  22. [22]

    O’Brien, Louis Rosenberg, and Dawn Song

    Vivek Nair, Wenbo Guo, Justus Mattern, Rui Wang, James F. O’Brien, Louis Rosenberg, and Dawn Song. Unique identification of 50,000+ virtual reality users from head & hand motion data, 2023. URLhttps://arxiv.org/abs/2302.08927

    work page arXiv 2023

  23. [23]

    A behaviour biometrics dataset for user identification and authentication.Data in Brief, 45:108728, 11 2022

    Nonso Nnamoko, Joe Barrowclough, Mark Liptrott, and Ioannis Korkontzelos. A behaviour biometrics dataset for user identification and authentication.Data in Brief, 45:108728, 11 2022. doi: 10.1016/j.dib.2022.108728

    work page doi:10.1016/j.dib.2022.108728 2022

  24. [24]

    Papamichail, Kyriakos C

    Michail D. Papamichail, Kyriakos C. Chatzidimitriou, Thomas Karanikiotis, Napoleon- Christos I. Oikonomou, Andreas L. Symeonidis, and Sashi K. Saripalle. Brainrun: A be- havioral biometrics dataset towards continuous implicit authentication.Data, 4(2), 2019. ISSN 2306-5729. doi: 10.3390/data4020060. URL https://www.mdpi.com/2306-5729/4/2/60

    work page doi:10.3390/data4020060 2019

  25. [25]

    PureSkill.gg competitive CS:GO gameplay dataset

    PureSkill.gg. PureSkill.gg competitive CS:GO gameplay dataset. AWS Data Exchange, 2021. URLhttps://docs.pureskill.gg/datascience/

    work page 2021

  26. [26]

    Who is alyx? a new behavioral biometric dataset for user identification in xr.Frontiers in Virtual Reality, 4, November 2023

    Christian Rack, Tamara Fernando, Murat Yalcin, Andreas Hotho, and Marc Erich Latoschik. Who is alyx? a new behavioral biometric dataset for user identification in xr.Frontiers in Virtual Reality, 4, November 2023. ISSN 2673-4192. doi: 10.3389/frvir.2023.1272234. URL http://dx.doi.org/10.3389/frvir.2023.1272234

    work page doi:10.3389/frvir.2023.1272234 2023

  27. [27]

    Valorant

    Riot Games. Valorant. https://playvalorant.com/, 2020. Video game; Published region- ally by Tencent Games (CN) and Taiwan Mobile (TW)

    work page 2020

  28. [28]

    Continuous user authentication using mouse dynamics, machine learning, and minecraft

    Nyle Siddiqui, Rushit Dave, and Naeem Seliya. Continuous user authentication using mouse dynamics, machine learning, and minecraft. In2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), pages 1–6, 2021. doi: 10.1109/ICECET52533. 2021.9698532. 12

    work page doi:10.1109/icecet52533 2021

  29. [29]

    Profiling in games: Understanding behavior from telemetry

    Rafet Sifa, Anders Drachen, and Christian Bauckhage. Profiling in games: Understanding behavior from telemetry. 2018. URL https://api.semanticscholar.org/CorpusID: 58984151

    work page 2018

  30. [30]

    Beacon: A multimodal dataset for learning behavioral fingerprints from gameplay data, 2026

    Ishpuneet Singh, Gursmeep Kaur, Uday Pratap Singh Atwal, Guramrit Singh, Gurjot Singh, and Maninder Singh. Beacon: A multimodal dataset for learning behavioral fingerprints from gameplay data, 2026. URL https://huggingface.co/datasets/beacon-gui/ BEACON-Dataset

    work page 2026

  31. [31]

    Beacon-logger: A behavioral authentication and network traffic logger for game environments, 2026

    Ishpuneet Singh, Guramrit Singh, Gursmeep Kaur, Uday Pratap Singh Atwal, Gurjot Singh, and Maninder Singh. Beacon-logger: A behavioral authentication and network traffic logger for game environments, 2026. URLhttps://zenodo.org/records/20062628

    work page arXiv 2026

  32. [32]

    Balagani

    Zdeˇnka Sitová, Jaroslav Šedˇenka, Qing Yang, Ge Peng, Gang Zhou, Paolo Gasti, and Kiran S. Balagani. Hmog: New behavioral biometric features for continuous authentication of smart- phone users.IEEE Transactions on Information Forensics and Security, 11(5):877–892, 2016. doi: 10.1109/TIFS.2015.2506542

    work page doi:10.1109/tifs.2015.2506542 2016

  33. [33]

    Tdas: A touch dynamics based multi-factor authentication solution for mobile devices.International Journal of Pervasive Computing and Communications, 12(1):127–153, 2016

    Pin Shen Teh, Ning Zhang, Andrew Beng Jin Teoh, and Ke Chen. Tdas: A touch dynamics based multi-factor authentication solution for mobile devices.International Journal of Pervasive Computing and Communications, 12(1):127–153, 2016. doi: 10.1108/IJPCC-01-2016-0005

    work page doi:10.1108/ijpcc-01-2016-0005 2016

  34. [34]

    Strengthen user authentication on mobile devices by using user’s touch dynamics pattern

    Pin Shen Teh, Ning Zhang, Syh-Yuan Tan, Qi Shi, Wee How Khoh, and Raheel Nawaz. Strengthen user authentication on mobile devices by using user’s touch dynamics pattern. Journal of Ambient Intelligence and Humanized Computing, 11(10):4019–4039, 2020. doi: 10.1007/s12652-019-01654-y

    work page doi:10.1007/s12652-019-01654-y 2020

  35. [35]

    Obaidat, Youssef Nakkabi, and Iris Lai

    Issa Traore, Isaac Woungang, Mohammad S. Obaidat, Youssef Nakkabi, and Iris Lai. Combining mouse and keystroke dynamics biometrics for risk-based authentication in web environments. In2012 Fourth International Conference on Digital Home, pages 138–145, 2012. doi: 10.1109/ ICDH.2012.59

    work page 2012

  36. [36]

    Using biometric data to measure and predict emotional engagement of video games

    Janette Vazquez, Samir Abdelrahman, Chris Wasden, Stuart Jardine, Colby Judd, Mathew Davis, and Julio Facelli. Using biometric data to measure and predict emotional engagement of video games. 03 2022. doi: 10.1101/2022.02.28.482337

    work page doi:10.1101/2022.02.28.482337 2022

  37. [37]

    In: 2020 IEEE Symposium on Security and Privacy (SP)

    Meiqi Wang, Yanzeng Li, Xuebin Wang, Tingwen Liu, Jinqiao Shi, and Muqian Chen. 2ch-tcn: A website fingerprinting attack over tor using 2-channel temporal convolutional networks. In 2020 IEEE Symposium on Computers and Communications (ISCC), pages 1–7, 2020. doi: 10.1109/ISCC50000.2020.9219717

    work page doi:10.1109/iscc50000.2020.9219717 2020

  38. [38]

    Esta: An esports trajectory and action dataset, 2022

    Peter Xenopoulos and Claudio Silva. Esta: An esports trajectory and action dataset, 2022. URL https://arxiv.org/abs/2209.09861

    work page arXiv 2022

  39. [39]

    signal" is significantly stronger than the background

    Franziska Zimmer, Mhd Irvan, Maharage Nisansala Sevwandi Perera, Ryosuke Kobayashi, and Rie Shigetomi Yamaguchi. Fair play and identity: In-game behavioral biometrics for player identification in competitive online games. In2025 IEEE Conference on Games (CoG), pages 1–8, 2025. doi: 10.1109/CoG64752.2025.11114281. 13 A Ethics Statement Consent, oversight, ...

    work page doi:10.1109/cog64752.2025.11114281 2025