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

2026-05-11

AI Summary

This work addresses the scarcity of large-scale, multimodal, and contextually synchronized fine-grained behavioral datasets in high-risk digital environments, which has hindered advances in continuous authentication research. To bridge this gap, we introduce the BEACON dataset, collected from 28 players across 79 sessions in the competitive game *Valorant*. It comprises synchronized high-frequency mouse trajectories, keyboard events, network packets, screen recordings, hardware metadata, and game configuration settings. BEACON is the first dataset to integrate cognitive load and fine motor skills within a high-fidelity esports setting, offering 102.51 hours (approximately 430 GB) of authentic behavioral data. The dataset supports user drift analysis and multimodal representation learning, and is publicly released on Hugging Face and GitHub to establish a reproducible benchmark for behavioral biometrics and cybersecurity research.

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

Problem

• continuous authentication
• behavioral biometrics
• multimodal dataset
• user drift
• esports

Innovation

• multimodal dataset
• behavioral biometrics
• continuous authentication
• esports
• user behavioral fingerprinting