> For the complete documentation index, see [llms.txt](https://cartoonmango-1.gitbook.io/vida-ekyc-integration/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cartoonmango-1.gitbook.io/vida-ekyc-integration/integration-methods/sdk/overview/screen-detection.md).

# Screen Detection

VIDA's passive liveness detection discerns a physically present human from spoof artifacts in single-shot images. This feature reduces friction during capture, ensuring the person is genuinely present and not using doctored images or videos.

**Authenticity Evaluation**

The system evaluates the authenticity of a selfie by analyzing various aspects to confirm if the depicted person is truly present. It detects various attack vectors, including 2D paper photos, mobile screen attacks, etc.

**Liveness Scoring:**

* Liveness Score Range: 0 (maximum liveness) to 1 (minimum liveness)
* Customizable acceptance threshold for specific risk appetite.
* Tradeoff between False Acceptance Rate (FAR) and False Rejection Rate (FRR).

**Liveness Scoring Customization:**

* FAR: Less than 1%
* FRR: Less than 1%

**Attack Presentation Classification:**

* APCER (Attack Presentation Classification Error Rate): 1.25%
* NPCER (Normal Presentation Classification Error Rate): 1.25%