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

Hugging Face Daily Papers Papers
multimodal-dataset behavioral-biometrics continuous-authentication esports valorant security benchmark

Summary

BEACON is a large-scale multimodal dataset capturing behavioral signals from Valorant gameplay for continuous authentication and behavioral biometrics research.

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 Valorant gameplay. BEACON contains approximately 430 GB of synchronised modality data (461 GB total on-disk including auxiliary 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
Original Article
View Cached Full Text

Cached at: 05/14/26, 08:20 PM

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

Source: https://huggingface.co/papers/2605.10867

Abstract

BEACON is a large-scale multimodal dataset capturing diverse behavioral signals during competitive gaming to advance continuous authentication and behavioral biometrics research.

Continuous authenticationin 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-scalemultimodal datasetthat captures diverse skill tiers in competitive Valorant gameplay. BEACON contains approximately 430 GB of synchronised modality data (461 GB total on-disk including auxiliary 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 ofbehavioral biometrics. The dataset allows for the study ofcontinuous authentication,behavioral profiling,user driftandmultimodal representation learningin a high-fidelityesportssetting. The authors release the dataset and code on Hugging Face and GitHub to create a reproducible benchmark for evaluating next-generationbehavioral fingerprintingandsecurity models

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.10867

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.10867 in a model README.md to link it from this page.

Datasets citing this paper1

#### beacon-gui/BEACON-Dataset Preview• Updated1 day ago • 55 • 3

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.10867 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Beacon Biosignals is mapping the brain during sleep

MIT News — Artificial Intelligence

Beacon Biosignals is using a lightweight EEG headband and machine learning to map brain activity during sleep, aiming to create a foundation model for brain health and accelerate clinical trials for neurological disorders.

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models

arXiv cs.CL

RedBench introduces a universal dataset aggregating 37 benchmark datasets with 29,362 samples across 22 risk categories and 19 domains to enable standardized and comprehensive red teaming evaluation of large language models. The work addresses inconsistencies in existing red teaming datasets and provides baselines, evaluation code, and open-source resources for assessing LLM robustness against adversarial prompts.

GEESE: Genotype-aware End-to-End Spatio-temporal Embedding for Behavioral Phenotyping

arXiv cs.LG

GEESE is an end-to-end deep learning framework that learns behavioral representations directly from 3D pose dynamics without hand-crafted features, surpassing traditional baselines in behavior classification and genotype prediction across three autism-associated genetic models. It also introduces HONK, an interactive tool for natural language-based behavioral phenotyping.