---
title: "Biometric Fingerprint Spoofing Dataset"
description: "Contains 5,000+ high-quality fingerprint images capturing real fingerprints and multiple fingerprint spoofing attack types, including print and replay scenarios. Designed for spoofing detection and liveness…"
url: "https://unidata.pro/datasets/biometric-fingerprint-spoofing/"
date_modified: "2026-03-03T14:49:10+03:00"
language: "en-US"
---
Contains 5,000+ high-quality fingerprint images capturing real fingerprints and multiple fingerprint spoofing attack types, including print and replay scenarios. Designed for spoofing detection and liveness detection tasks, the fingerprint dataset provides labeled biometric data from different devices and fingers to train and evaluate biometric security and fingerprint recognition systems.

## Dataset Structure

### The Numbers Section

**Numbered list:**

- **Number:** 100 — **Text:** People
- **Number:** 5000+ — **Text:** Photos

### Tooltips Section

**Tooltip items:**

- **Name:** Computer Vision
- **Name:** Machine Learning
- **Name:** Image Processing
- **Name:** Security
- **Name:** Anti-Spoofing

### Dataset Information

**Table with data:**

| Characteristic | Data |
| --- | --- |
| Description | Fingerprint images were captured via three attack types: print, real, and replay |
| Data types | Image |
| Tasks | Spoof Detection, Classification |
| Number of images | 5000+ |
| Number of files in a set | 30 (10 real, 10 print, 10 replay) |
| Labeling | Metadata (gender, age, finger, hand, shooting device, display device, paper) |
| Total number of people | 100 |

**Media Slider:**

- **Image in the slider:** ![Biometric Fingerprint Spoofing Dataset](https://unidata.pro/wp-content/uploads/2026/02/spoof-dataset-cover2-rotated.webp)
- **Image in the slider:** ![Biometric Fingerprint Spoofing Dataset](https://unidata.pro/wp-content/uploads/2026/02/spoof-dataset-cover.webp)
- **Image in the slider:** ![Biometric Fingerprint Spoofing Dataset](https://unidata.pro/wp-content/uploads/2026/02/spoof-dataset-cover3-rotated.webp)

**Link to the sample:** [Download sample](https://drive.google.com/drive/folders/1S2jH8Xj60b2ASZnPoiUoyGn1ZmXIn0Nb)

### Technical Specifications

**Table with data:**

| Characteristic | Data |
| --- | --- |
| Image Extension | JPG |
| Device | iPhone, Samsung, OPPO |

**Source and data collection methodology:** Source and collection methodology: Data was collected by Unidata team in a rented studio.

### Dataset Use Cases - Slider

**Industry Cards:**

- **Industry:** Biometric Security — **Title:** Fingerprint Spoofing Detection for Secure Access — **Text:** This fingerprint spoofing dataset is used to train spoofing detection and liveness detection models in biometric security systems. It combines real fingerprints with synthetic and replay-based spoofing attacks, helping detection algorithms recognize fake fingerprints and improve biometric authentication accuracy in access control and security systems.
- **Industry:** Mobile & Consumer Devices — **Title:** Strengthening Fingerprint Authentication on Sensors — **Text:** Fingerprint scanners in smartphones face spoofing fingerprint attacks using printed and replayed biometric data. This fingerprint dataset supports training data for biometric systems by exposing models to realistic attack scenarios, varied fingers, and devices, improving recognition performance and reliable user authentication on consumer devices.
- **Industry:** Financial Services — **Title:** Anti-Spoofing for Biometric Verification Systems — **Text:** Banks and digital payment platforms rely on biometric authentication to verify user identity. This biometric spoofing dataset enables detecting spoofing attempts during fingerprint verification by modeling presentation attacks, fake biometric patterns, and real fingerprints, strengthening fraud prevention and improving security systems in financial workflows.
- **Industry:** Research & Algorithm Development — **Title:** Benchmarking Biometric Spoofing and Liveness Models — **Text:** Researchers use this fingerprint spoofing dataset to benchmark spoofing detection, liveness detection, and fingerprint recognition algorithms. The labeled biometric data, multiple attack types, and detailed metadata support reproducible experiments, deep learning training, and evaluation of biometric security solutions across realistic attack conditions.

### Fact

**FAQs Heading:** FAQs

**List of Questions:**

- **Question:** Can I request a sample of the fingerprint dataset before purchasing? — **Answer:** Yes, a free sample of the fingerprint dataset is available for evaluation and testing. This allows you to review real fingerprints, fake fingerprints, and metadata structure before committing to the full dataset.
- **Question:** What types of annotations are provided with the dataset? — **Answer:** Each fingerprint image includes detailed metadata such as finger type, hand, gender, age, capture device, display device, and paper type. These labels support advanced pattern recognition, attack detection, and recognition performance analysis.
- **Question:** How was the data collected? — **Answer:** All fingerprint images were captured by the Unidata team in a rented studio using mobile devices under controlled conditions.
- **Question:** How are Unidata fingerprint datasets licensed? — **Answer:** Unidata datasets follow a dual-licensing model where free samples are provided for testing, while full datasets are available through purchase. This structure supports both experimentation and production-grade biometric technology development.
- **Question:** Do Unidata datasets comply with GDPR and data privacy laws? — **Answer:** Yes, all biometric datasets are curated in full compliance with GDPR and applicable data protection regulations. Data is collected ethically from legally permissible sources to ensure privacy and lawful usage.
- **Question:** How are biometric datasets stored and secured? — **Answer:** All fingerprint data is securely stored on AWS cloud infrastructure with controls aligned to ISO 27001 and ISO 27701 standards. This ensures strong biometric data protection, scalability, and secure access management.
- **Question:** How long does it take to receive the fingerprint spoofing dataset? — **Answer:** After submitting a request, the Unidata team reviews the requirements and completes documentation. Once signed and paid, the dataset is delivered within 3–10 days.
- **Question:** Why is spoof attack data important for training fingerprint recognition models? — **Answer:** Spoof attack examples allow machine learning models to understand the differences between authentic fingerprints and artificial replicas. This improves the robustness of biometric systems used in identity verification and access control applications.

[Full list of this site's AI-readable pages](https://unidata.pro/llms.txt)