# Identity Check

### About service

An Identity Check is a **biometric identity verification** service for **KYC onboarding**.

It combines **ISO-certified (PAD Level 2) selfie liveness detection** with **facial similarity (face match)** to verify that a customer is the genuine person behind an identity. It compares a live selfie with the photo on an official ID document. It returns a liveness outcome and a facial similarity confidence score.

To protect your identity verification flow from spoofing, ComplyCube uses **Presentation Attack Detection (PAD)**. This helps detect common **liveness fraud** vectors, including:

* **Printed mask attacks**: Where masks with cut-outs are used to mimic real faces.
* **Printed photo attacks:** Where fraudsters use printed photos.
* **Image replay attacks:** Where injected images attempt to simulate liveness.
* **3D mask attacks**: Where silicone or plastic masks are used to impersonate individuals.

By combining face match with real-time liveness detection, Identity Check helps reduce onboarding fraud. It’s commonly used for **KYC identity verification**, **customer onboarding**, **transaction approvals**, and more

If you need higher assurance with video challenges, use [Enhanced Identity Check](/documentation/product-guides/biometric-and-liveness-verification/enhanced-identity-check.md).

{% hint style="info" %}
On a successful Identity Check, your customer’s facial biometrics will be **automatically enrolled** (if enabled on your plan). This helps prevent fraud related to multiple registrations under different identities and enables [face-based authentication](/documentation/product-guides/biometric-and-liveness-verification/face-authentication-check.md) for future interactions.
{% endhint %}

{% hint style="info" %}
Even though it is possible to run this check entirely through our API, we **highly recommend** that you run it through our [Hosted Solution](/documentation/sdks/web-integrations/hosted-solution-quick-guide.md), [Web SDK](/documentation/sdks/web-integrations/web-sdk-quick-guide.md), or native [Mobile SDKs](/documentation/quick-guides/mobile-sdk-guide.md). These SDKs guide your clients through the capture process, aiding them with completing the flow successfully with minimal friction and false-positive outcomes.
{% endhint %}

{% hint style="info" %}
[Learn about the Identity Checks API.](/documentation/api-reference/check-types/identity-check.md)
{% endhint %}

### Analysis performed

An Identity Check runs layered **biometric analysis** to validate **liveness**, confirm **facial similarity**, and flag **spoofing** or tampering signals.

The diagram below outlines the key analysis categories.

***

![Identity Check Overview](/files/-MV1OAM6OklgKz5HbAmz)

***

**Detailed verification checks**

<table><thead><tr><th width="205.12890625">Analysis</th><th>Verifications Performed</th></tr></thead><tbody><tr><td><strong>Face Analysis</strong></td><td><ul><li><strong>Facial similarity</strong>: Compares the submitted selfie with the ID photo to confirm both belong to the same person. Returns a confidence score between 0–100%, where 100% indicates a perfect match and 0% indicates no match at all.</li><li><strong>Banned faces analysis</strong>: Flags matches against prohibited or blacklisted face databases.</li><li><strong>Previously enrolled face</strong>: Detects if the same face has already been registered using different customer details.</li></ul></td></tr><tr><td><strong>Authenticity Analysis</strong></td><td><ul><li><strong>Spoofed image analysis</strong>: Indicates whether the images are manipulated, copied from the internet, or are known blacklisted images.</li><li><p><strong>Liveness check</strong>: Confirms the customer is physically present and not a spoof attempt. This involves advanced biometric and anti-spoofing techniques, such as:</p><ul><li>3D facial mapping</li><li>Skin texture and micro-expression analysis</li><li>Pixel-level tampering detection</li><li>Virtual camera detection</li><li>Mask and disguise recognition</li><li>Proprietary anti-spoofing techniques</li></ul><p>Returns a confidence score between 0–100%, where 100% indicates a highly reliable live presence and 0% indicates a likely spoof attempt.</p></li></ul></td></tr><tr><td><strong>Integrity Analysis</strong></td><td><ul><li><strong>Face detection</strong>: Ensures the expected number of faces are present in the image and that the image quality is sufficient for reliable analysis.</li></ul></td></tr></tbody></table>

### Check duration

An Identity Check takes an average of **3 seconds** to complete.

### Related checks

You’ll typically run an Identity Check alongside:

* [Document Check](/documentation/product-guides/identity-verification/document-check.md) for document authenticity and ID data extraction.
* [AML Screening Check](/documentation/product-guides/watchlist-pep-and-adverse-media/aml-screening-check.md) for sanctions, PEP, and adverse media screening.
* [Multi-Bureau Check](/documentation/product-guides/identity-verification/multi-bureau-check.md) for identity and address verification via authoritative sources.
* [Face Authentication Check](/documentation/product-guides/biometric-and-liveness-verification/face-authentication-check.md) for step-up and repeat authentication after enrolment.

### Related topics

Use these when building end-to-end KYC journeys that include Identity Check:

* [Workflows](/documentation/product-guides/compliance-studio/workflows.md) to bundle Identity Check into a single customer journey.
* [Compliance Policies](/documentation/product-guides/compliance-studio/policies.md) to apply rule-based decisions and evidence requirements.
* [Hosted Solution](/documentation/sdks/web-integrations/hosted-solution-quick-guide.md), [Web SDK](/documentation/sdks/web-integrations/web-sdk-quick-guide.md), and [Mobile SDKs](/documentation/quick-guides/mobile-sdk-guide.md) for guided selfie capture.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.complycube.com/documentation/product-guides/biometric-and-liveness-verification/identity-check.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
Analysis	Verifications Performed
Face Analysis	Facial similarity: Compares the submitted selfie with the ID photo to confirm both belong to the same person. Returns a confidence score between 0–100%, where 100% indicates a perfect match and 0% indicates no match at all. Banned faces analysis: Flags matches against prohibited or blacklisted face databases. Previously enrolled face: Detects if the same face has already been registered using different customer details.
Authenticity Analysis	Spoofed image analysis: Indicates whether the images are manipulated, copied from the internet, or are known blacklisted images. Liveness check: Confirms the customer is physically present and not a spoof attempt. This involves advanced biometric and anti-spoofing techniques, such as: 3D facial mapping Skin texture and micro-expression analysis Pixel-level tampering detection Virtual camera detection Mask and disguise recognition Proprietary anti-spoofing techniques Returns a confidence score between 0–100%, where 100% indicates a highly reliable live presence and 0% indicates a likely spoof attempt.
Integrity Analysis	Face detection: Ensures the expected number of faces are present in the image and that the image quality is sufficient for reliable analysis.