Introduction
This dataset focuses on 3D volume based paper attack. Actors present flat photos, cut‑outs, and wearable paper masks while performing active‑liveness gestures. Those are considered advanced paper attacks useful for iBeta level 2 liveness tests
Dataset summary
This Advanced 3D Paper Mask Attack Dataset specializes in volumetric presentation attacks for advanced Presentation Attack detection (PAD) training. Masks on actors using external attributes, which ensures realism – essential for iBeta Level 2 liveness certification preparation
Dataset features
- 25 participants recorded under signed consent
- Dual-device capture: iOS / Android phones
- Diverse representation: balanced gender mix and broad ethnicity coverage (Caucasian, Black, Asian, Latinx)
- 5 000 videos
- Active-liveness phases: fixed, zoom-in, zoom-out
Types of Attacks
1. Printed attributes on photo – a flat facial photo with accessories (e.g., glasses, hat) printed together with the face
2. Cut-out attributes in photo – a flat facial photo cut to the shape of the face
3. External attributes on top of photo – a flat facial photo with real accessories (glasses, cap, etc.) attached on top
4. Photo mask on actor + external attributes – a full-size photo fixed to an actor’s face; real items such as a hood or wig are added
5. Photo mask on actor, printed attributes – a fixed photo that already contains additional printed attributes
6. Photo mask on actor with eye holes + external attributes – eye openings are cut in the photo; the actor blinks through them while wearing real wig/clothing
7. Photo mask with printed attributes and eye holes – combines printed accessories on the photo with the actor’s live eyes visible through cut-outs
Advanced Attack Scenarios
- Testing: Zoom in/out phases included
- Variable Paper Types: Multiple paper textures and qualities
- Environmental Variations: Different lighting and background conditions
Technical Specifications
- Multi-Device Compatibility: Low-end to high-end capture devices
- Resolution Variety: Multiple capture qualities for robust training
- Standardized Format: Compatible with major ML frameworks
- Quality Assurance: Professional data collection standards
Use Cases & Applications
- Liveness Detection Model Training: High-accuracy spoofing detection
- iBeta Certification Preparation: Pre-certification model validation
- Anti-Spoofing Research: Academic and commercial research projects
- Biometric Security Systems: Enterprise-grade authentication solutions
- Facial Recognition Enhancement: Improved security layer implementation
How industry leaders achieve superior liveness detection with our dataset
Fintech Company from Brazil: iBeta Level 1 Success
One of the largest fintechs in Brazil approached us to prepare an active biometric authentication system for iBeta Level 1 certification
Digital Bank from Vietnam: iBeta Level 2 success
Digital bank from Vietnam asked Axon Labs to prepare its anti-spoofing model in order to pass iBeta Level 2 on the first attempt, and the goal was achieved
Financial institution in LatAm: iBeta Level 1 & 2 Success
A leading financial infrastructure player in Latin America successfully obtained iBeta Level 1 and Level 2 certifications, relying on data provided by Axon Labs
Potential customisation options:
- Filming videos attacks with targeted movements (E.g. – Zoom In / Zoom Out)
- Filming videos attacks for you on target devices (for example, webcams)
- Using your SDK for custom attack scenarios spoofing your ML model
- Use RGB and USB cameras to support diverse research and testing needs
Related Datasets
We have a simplified version of this dataset in our collection: 3D Paper Mask Attacks dataset. You may also be interested in: Wrapped 3D Attacks Dataset
Legal & Compliance
We prioritize data privacy, ethical AI development, and regulatory compliance. Our Silicone Mask Attack Dataset is collected and processed in full accordance with global data protection standards including GDPR, ensuring legality, security, and responsible AI practices
Sample dataset
A sample version of this dataset is available on Kaggle. Leave a request for additional samples in the form below
Have a question?
We collect data from our internal team. All information is further verified by our specialists
Once your enquiry has been sent, we will contact you to discuss the details and complete the necessary paperwork. The timing of receiving the dataset depends on the specific request and additional requirements
Our unique selling point is to provide legally clean datasets to our customers. We obtain the consent from all the participants to use their data for AI model development. We are able to provide comprensive reporting on the licensing, data collection and privacy compliance of our datasets. Although there seems to be a diverse response to how to control AI development and deployment, we are able to service global customers seeking to launch global AI products.
The dataset follows iBeta testing protocols and includes diverse attack scenarios that mirror real-world spoofing attempts. It covers both passive and active liveness testing requirements with proper demographic representation and standardized capture conditions essential for certification preparation
The price depends on your specific requirements. Please submit a request to receive a free consultation
Contact us
Tell us about yourself, and get access to free samples of the dataset
Didn't find what you were looking for?
Our collection includes many datasets for various requests
iBeta Level 1 Paper
– 22,000+ videos
– 80+ participants
– zoom in and
zoom out
Replay Display attacks
– 5,000+ videos
– 1,000+ participants
– Balanced mix of genders and ethnicities
Photo Print Dataset
– 7000+ videos.
– 10-20 second each video
– Mix of genders
Silicone Mask Dataset
– 10 000+ videos
– 18 Silicone Masks
– iBeta Level 2
Liveness Detection
