> For the complete documentation index, see [llms.txt](https://docs.vida.id/identity-stack/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.vida.id/identity-stack/verify/liveness/integration/liveness-sdk/liveness-fraud-ops.md).

# Liveness Fraud Ops

## What is Liveness Fraud Ops?

VIDA Liveness Fraud Ops is a **near-real-time manual fraud review** system for VIDA liveness service. When your system accepts a user's liveness check based on VIDA’s automated evaluation, Fraud Ops **intercepts that session for deeper inspection** — especially when the session score passes the AI threshold but may still exhibit signs of spoofing.

With a specially-trained & quality-controlled human agents, VIDA does secondary review for transaction passing AI-based liveness checking, flags whether the transaction is genuine or fraudulent, and sends you the result via webhook or API — all within up to 15 minutes. If the session is flagged as fraud (e.g., deepfake), your backend can immediately take action according to your business process (e.g.: block the transaction, blacklist the user, or so on)

## Key Benefits <a href="#key-benefits" id="key-benefits"></a>

<table><thead><tr><th width="245.08868408203125">Benefit</th><th>Key Value</th></tr></thead><tbody><tr><td><strong>Rapid Fraud Interception</strong></td><td>Detect and act on suspicious liveness sessions within 15 minutes.</td></tr><tr><td><strong>Additional Human Expertise for AI edge cases</strong></td><td>Specially-trained &#x26; quality-controlled agents do secondary checking to identify AI biases &#x26; bypasses</td></tr><tr><td><strong>Protection Against High-Impact Fraud</strong></td><td>Especially valuable for enterprises in finance, fintech, telcos, and e-commerce dealing with high-value transactions.</td></tr><tr><td><strong>Clear Spoof Reason</strong></td><td>You will receive detailed fraud classification and justification (e.g.: Injection Attack - Watermark)</td></tr></tbody></table>

## Supported Products

VIDA Liveness Fraud Ops supports following product:

<table><thead><tr><th width="398.8984375">VIDA Product</th><th>Reference</th></tr></thead><tbody><tr><td><strong>Liveness API</strong></td><td><a data-mention href="/pages/jQ6q5orvRchohzA4DhaX">/pages/jQ6q5orvRchohzA4DhaX</a></td></tr><tr><td><strong>Liveness SDK</strong></td><td><a data-mention href="/pages/4fdjq4oSP5m3MxZNPm9P">/pages/4fdjq4oSP5m3MxZNPm9P</a></td></tr><tr><td><strong>Liveness module inside Identity Verification API</strong></td><td><a data-mention href="/pages/TOi7Cdju5QLdJ3Nq27Sa">/pages/TOi7Cdju5QLdJ3Nq27Sa</a></td></tr></tbody></table>

## How Fraud Ops Works

* **Trigger**: A liveness session that passes VIDA’s AI (accepted) check is routed to a **human reviewer** if:
  * Fraud Ops is enabled for your integration configuration.
  * The liveness score is within accepted threshold (e.g., <0.95).
* **Agent Review**: A trained VIDA agent reviews the selfie:
  * Is it a real human, or a spoof (deepfake, static image, mask, etc.)?
* **Result Notification**:
  * If photo turns out to be spoof → a webhook notification is sent to your backend.
  * Alternatively, you can pull status via the [ID Fraud Shield Disabled](/identity-stack/verify/liveness/integration/api/api-reference/liveness-transaction-details-api/id-fraud-shield-disabled.md)
* **Your Action**: Once a spoof notification is received, you can take action depending on your business process (e.g.: block the transaction, blacklist the user, or so on)