Skip to content
AI News HubLIVE
Original source2 min read

Long-Range Video Presentation Attack Detection: A Three-Class Benchmark Across 1-100 m and Two Sensor Types

Summary

Researchers introduce a video-based presentation attack detection dataset of 374,000+ frames from 261 identities across five standoff distances (1–100 m) under indoor/outdoor conditions, using DSLR and mobile sensors with three-class labels: live, spoof, and props. Benchmarks show DSLR maintains near-perfect spoof detection at all distances, while mobile sensor performance degrades sharply beyond 50 m; EfficientNet achieves 98.48% accuracy.

SourcearXiv Machine LearningAuthor: Lambert Igene, Mohammad Zahir Uddin Chowdhury, Afzal Hossain, Sandip Purnapatra, Peter Johnson, Stephanie Schuckers
Long-Range Video Presentation Attack Detection: A Three-Class Benchmark Across 1-100 m and Two Sensor Types
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Nov 2026]

Title:Long-Range Video Presentation Attack Detection: A Three-Class Benchmark Across 1-100 m and Two Sensor Types

View a PDF of the paper titled Long-Range Video Presentation Attack Detection: A Three-Class Benchmark Across 1-100 m and Two Sensor Types, by Lambert Igene and 5 other authors

View PDF HTML (experimental)

Abstract:Face presentation attack detection (PAD) systems deployed in border control and airport surveillance are constrained by a critical assumption: subjects are captured at close range, typically under one meter. No existing benchmark systematically addresses multi-distance capture, diverse environmental conditions, and concurrent spoofing and occlusion-based attacks, leaving deployed models underprepared for real-world scenarios. We introduce a video-based PAD dataset of 374,000+ frames from 261 unique identities collected across five standoff distances (1 m-100 m) under indoor and outdoor conditions using a DSLR camera (C) and a mobile sensor (M), with three-class labels: live, spoof, and props (occlusions); models are trained and evaluated on video clips rather than single frames. We fine-tune and benchmark four CNN architectures: MobileNetV3, MobileNet, EfficientNet, and ResNet-50. The higher-resolution DSLR maintains near-perfect spoof classification rate across all distances, while the lower-resolution mobile sensor degrades sharply beyond 50 m, with props classification rate dropping to 55% at 75 m for MobileNetV3. EfficientNet achieves the best overall performance (98.48% accuracy, ACER 2.01%). Generalization tests on unseen attack datasets yield 89-94% accuracy, validating cross-domain robustness. These results establish capture distance and sensor resolution as critical but underexplored axes of PAD difficulty. The dataset will be publicly released under an End-User License Agreement to support reproducible long-range PAD research.

Comments: 10 page, IJCB

Subjects:

Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.25108 [cs.LG]

(or arXiv:2611.25108v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.25108

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Lambert Igene [view email] [v1] Wed, 18 Nov 2026 19:41:53 UTC (6,054 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Long-Range Video Presentation Attack Detection: A Three-Class Benchmark Across 1-100 m and Two Sensor Types, by Lambert Igene and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs cs.CV

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Dataset contains 374,000+ frames from 261 identities across 1–100 m and indoor/outdoor conditions
  • Three-class labels—live, spoof, props (occlusions)—with video-clip-based training and evaluation
  • DSLR maintains near-perfect spoof classification across distances; mobile sensor drops sharply beyond 50 m
  • EfficientNet leads with 98.48% accuracy and ACER 2.01%; cross-domain generalization reaches 89–94%

Highlights and analysis are generated automatically and may contain errors. Check the original source.