BEACON

Behavioral Engine for Authentication and Continuous Monitoring

BEACON is a research initiative dedicated to leveraging gameplay behavior as a biometric signal for continuous authentication and zero-trust security architectures. We design high-fidelity acquisition frameworks and scalable machine learning systems to identify users based on unique interaction signatures.

🔬 Core Research Areas

• Gameplay Fingerprinting: Identifying users via high-resolution input dynamics.
• Behavioral Biometrics: Modeling keystroke dynamics, mouse kinematics, and network traffic.
• Continuous Authentication: Enabling passive, non-intrusive security layers for gaming and enterprise environments.

📊 The BEACON Dataset

The BEACON Dataset is a high-fidelity multimodal collection comprising 445 GB of telemetry across 28 participants and 79 sessions. It features synchronized logs of keyboard events, mouse movement, network traffic, and screen recordings captured via the BEACON-Logger suite.

⭐️ Resources & Access

• Hugging Face Data Link: https://huggingface.co/datasets/beacon-gui/BEACON-Dataset
• Zenodo Dataset Link: https://doi.org/10.5281/zenodo.20034625
• Zenodo Logger Link: https://doi.org/10.5281/zenodo.20062628

📄 Publications & Citations

If you utilize this dataset or the collection framework, please cite the following:

Dataset: Singh, I., Kaur, G., Atwal, U. P. S., Singh, G., Singh, G., & Singh, M. (2026). BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data [Data set]. Zenodo. https://doi.org/10.5281/zenodo.20034625

Logger: Singh, I., Singh, G., Kaur, G., Atwal, U. P. S., Singh, G., & Singh, M. (2026). BEACON-Logger: A Behavioral Authentication and Network Traffic Logger for Game Environments. Zenodo. https://doi.org/10.5281/zenodo.20062628

Technical Paper (Preprint):

@misc{singh2026beaconmultimodaldatasetlearning,
      title={BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data}, 
      author={Ishpuneet Singh and Gursmeep Kaur and Uday Pratap Singh Atwal and Guramrit Singh and Gurjot Singh and Maninder Singh},
      year={2026},
      eprint={2605.10867},
      archivePrefix={arXiv},
      primaryClass={cs.CR},
      url={https://arxiv.org/abs/2605.10867}, 
}

👥 Authors & Contact

This project is a collaborative effort between researchers from Thapar Institute of Engineering and Technology and the University of Waterloo: