---
title: "Ethnic Coverage Expansion for iBeta Level 1 Certification"
description: "A model reporting 91% accuracy read as certification-ready. Split by ethnicity, the number told a different story."
url: "https://unidata.pro/cases/ethnic-coverage-expansion-for-ibeta-level-1-certification/"
date_modified: "2026-09-02T06:09:31+03:00"
language: "ru-RU"
---
**The Problem**
---------------

A client's face-biometric model couldn't reliably recognize faces across diverse ethnic groups. In-house and open-source data skewed heavily European, and accuracy sat around 91% for some ethnicities, which is low enough to fail Level 1, with launch delays, market-access limits, and contractual risk behind it.

- Limited diversity: predominantly European faces, little ethnic range.
- Too few real-world attack scenarios for underrepresented groups, weakening robustness exactly where the model was already weakest.

**Solution**
------------

- A tailored Level 1 dataset with 50 actors across a wide ethnic range (60% Caucasian, 20% African, 20% Asian).
- Each actor performed multiple presentation attacks — photos, masks, and replays.
- Integrated with the client's existing data to raise coverage where it was thinnest.
- Real-world scenarios and high-resolution video met iBeta's lab requirements and minimized Type I and Type II errors.

| Phase | Input | Scope of Work | Quality Control |
|---|---|---|---|
| Model & Requirements Intake | Client's face-biometric model, target Level 1 scope | Access setup; identifying which ethnic groups drive the 91% ceiling | Weak groups named, not averaged into a single score |
| Coverage Gap Review | In-house + open-source data | Auditing ethnic distribution and attack coverage per group | Underrepresented groups documented against Level 1 requirements |
| Dataset Assembly | Tailored Level 1 set (50 actors) | Actors across the required ethnic range, each through photo, mask, and replay attacks | Ethnic coverage and attack types confirmed per actor |
| Integration & Retraining | Delivered dataset + client data | Merging new coverage with existing data and retraining | Coverage raised where it was thinnest |
| Validation & Error Analysis | Model inference results | Accuracy breakdown by ethnicity; checking Type I / II balance | Improvement holds across all groups, not just the average |
| Pre-Check & Handoff | Retrained model, final dataset | Level 1 pre-check; report and data handoff | Client sign-off; model cleared for lab submission |

## Main title

Ethnic Coverage Expansion for iBeta Level 1 Certification

## Description

A client’s face-biometric model reported roughly 91% accuracy, close enough to look certification-ready. Broken out by ethnicity, performance ranged from near-perfect on well-represented faces to far lower on underrepresented ones. iBeta grades the weakest group.

## Hero

**Project duration:** 21 days

## Прогресс - результаты - цитата

### Прогресс - шаги

**Перечень шагов:**

- **Количество дней:** Days 1–2 — **Описание шага:** Model & Requirements Intake
- **Количество дней:** Days 3–7 — **Описание шага:** Coverage Gap Review & Dataset Assembly
- **Количество дней:** Days 8–15 — **Описание шага:** Integration & Retraining
- **Количество дней:** Days 16–21 — **Описание шага:** Validation & Handoff

### Результаты

**Перечень результатов:**

- Accuracy rose from 91% to 98–99% across all ethnicities.
- Passed iBeta Level 1 on the first attempt.
- No additional training cycles; deployment stayed on schedule.

### Цитата

**Цитата:** You have to measure a coverage gap before you can close it. We ran fifty actors across a genuine ethnic range through photo, mask, and replay attacks, and that took the model from 91% to 98–99% accuracy that held up under lab conditions and not just on the client's own test data.

**Автор:** Kirill Meshyk

**Должность:** Head of Data Collection