Glossary

Which biometric verification solutions are best for detecting fraudsters registering multiple accounts with the same identity?

Fraudsters are getting smarter. They now often use stolen credentials or manipulated biometric data to claim promotions and bypass risk controls.

The issue is that, if you only use basic selfie matching, you might confirm the person matches an ID document, but you won't know if that same person has already signed up numerous times using different email addresses.

Therefore, effectively stopping these repeat attacks requires a combination of liveness detection, document verification, and biometric deduplication to flag duplicate identities in real time.

Biometric verification solutions that are best for this include, for example, GBG, Entrust and Veriff. In this article, we'll compare the ways these platforms can help you identify if the same face has appeared across different registration attempts to prevent issues like bonus abuse and account farming.

How to detect duplicate identities

As a global leader in identity technology, we've spent more than 30 years helping businesses connect safely with genuine customers. Our end-to-end identity verification platform, GBG Go, brings together multiple layers of biometric and document intelligence to ensure you aren't just verifying an identity, but detecting the behavior behind it.

Since we’ve written this article, we’ll cover our capabilities first and then introduce two alternative providers to consider.

By partnering with us, you can:

Verify identity ownership with advanced face matching and passive liveness

We use specialized algorithms to confirm that a person is real and present during onboarding. Our technology analyzes 68 biometric facial landmarks to securely link a customer-captured selfie to their photo ID. This process happens in seconds, providing a frictionless experience for remote identity proofing.

To stop impersonation, we also use certified passive liveness testing. This protects against presentation attacks by analyzing a customer's live image for signs of spoofing or digital screens. It requires no blinking or smiling – which, in turn, eliminates the potential for user error and makes the onboarding journey much smoother.

Identify suspicious account patterns with velocity checks

Confirming that an identity is genuine is only the first step. The real danger for many platforms, especially in sectors like iGaming, is the reuse of that legitimate identity across dozens of accounts.

Take gaming bonus abuse as an example. A user might verify their real identity, claim a signup bonus, and then open more accounts using the same face and ID.

We use velocity checks to identify when an individual has been seen multiple times within a specific period. This can help you detect repeat identity use and suspicious account creation patterns more quickly.

As David Thomas, Global Head of Product, Documents and Biometrics at GBG, notes:

“Bonus abuse in gaming is a good example of a case where the identity is legitimate, but the behavior isn't. Someone verifies their identity, gets the new-customer bonus, then opens a second account with a new email address and verifies the same identity again. That isn't fraud per se, but it is abuse, and our velocity checks will tell you that individual has been seen a certain number of times within a given period.”

Protect against deepfakes, face swaps and fraudulent documents with layered fraud detection

Sophisticated fraud rings now use AI to create face swaps and deepfakes. That’s why our biometric verification modules are built to detect 100% of deepfake injection attacks.

On the document side, we compare IDs against a library of 8,500 government-issued documents from 195 countries. This database is maintained by document experts using millions of real-world samples. Our tech performs up to 50 forensic authentication tests in seconds.

For biometrically chipped documents, we use NFC-enabled devices to digitally authenticate data with the issuer for the highest level of assurance. This includes enhanced tamper detection that is 98% effective at spotting modifications made after an ID was issued.

Entrust

Entrust offers a suite of tools focused on protecting the entire identity lifecycle. Its solution could be useful for organizations that need to build complex, multi-layered risk journeys.

With Entrust, you can:

Configure custom journeys: You can use Workflow Studio to layer biometric checks with additional signals and trusted data sources.
Identify returning faces: The Known Faces feature checks for faces that have appeared in the past year, flagging bad actors or existing users trying to create multiple accounts.
Detect repeat document use: The system notifies you if an identity document has been submitted before, even if the user tries to change attributes like the date of birth.
Automate motion liveness: Users take a video selfie and turn their head to prove presence, with 95% of these checks returning results in seconds.

Veriff

Veriff focuses on providing a highly automated and fast onboarding experience. Its AI-driven approach is designed to minimize the need for manual review while keeping pass rates high.

Veriff provides:

Face matching: AI analyzes and compares biometric templates from an authentication session against a stored template from the initial enrollment.
Passive liveness detection: The platform's passive liveness models validate that a user is real without requiring any unnatural movements. These models can spot masks, screens, and AI-generated selfies.
Actionable user feedback: Veriff's assisted image capture provides real-time guidance if lighting is poor or if a facial image is obstructed, which helps prevent technical failures.
One-second response: The fully automated facial analysis technology is built for speed, delivering results in approximately one second.

Why standard biometric verification isn't enough

Verifying that a face matches an ID is a good start, but it doesn't solve the problem of a single person owning a dozen different accounts.

The challenge of multi-accounting and repeat identity fraud

Fraudsters use multiple accounts to scale their operations. Be it account farming to manipulate social proof, money laundering to move illicit funds, or first-party fraud to exploit promotional offers, the goal is to stay under the radar by appearing as many different people.

Standard 1:1 checks only look at the current transaction. They are blind to the fact that the same face appeared two days ago in a different application.

What is biometric deduplication (1:N face matching)?

Standard 1:1 matching asks: does this person match this specific ID? Biometric deduplication, or 1:N matching, asks: has this face ever been seen in our database before?

This is important for high-volume onboarding because it identifies previously enrolled faces even if they use a different name or email address.

Some capabilities to look for in a biometric verification solution

When comparing providers, consider these features:

High face matching accuracy: Ability to handle different lighting, agesand camera qualities
Passive liveness detection: Ensuring the person is present without causing user drop-off
Deepfake detection: Spotting AI-generated video and image injection attacks
NFC authentication: Digitally verifying the data inside e-passports for maximum security
Global document coverage: Supporting thousands of ID types across different jurisdictions
Biometric deduplication: Flagging repeat faces to prevent multi-account creation
Risk-based workflows: Using risk signals to dynamically adjust the level of friction for each customer

Final thoughts

To stop fraudsters from creating multiple accounts, you need to move beyond the pass-or-fail of single identity checks. You need a solution that can look back across all previous enrollments to spot duplicates and stop abuse like account farming and bonus exploitation.

We provide a strong solution for this by combining global identity data with advanced biometric verification and cross-industry intelligence, ensuring you can onboard genuine customers while keeping repeat offenders out.

FAQs

What is biometric deduplication?

Biometric deduplication is a process that compares a new biometric sample, such as a face scan, against a database of previously enrolled users. This is used to identify if the same person is trying to register multiple times under different aliases.

How does biometric verification stop bonus abuse?

It identifies if a user has already registered and claimed a bonus by recognizing their unique facial features. Even if the user changes their email, IP address or phone number, their biometric landmarks remain the same, allowing the system to flag a duplicate account.

Why is passive liveness better than active liveness?

Passive liveness detection doesn't require the user to perform tasks like nodding or blinking. Because it’s faster and simpler, it significantly reduces customer drop-off rates during onboarding.

Can biometrics detect deepfakes?

Advanced biometric solutions use injection attack detection to identify when a video or image has been digitally altered or inserted into the camera feed. This allows the system to distinguish between a real human face and an AI-generated deepfake or face swap.

Sources:

*Disclaimer: Information relating to third-party products and companies referenced in this article is based on publicly available sources and official publications at the time of writing. While reasonable efforts have been made to ensure accuracy, product features, positioning and company information may change and GBG does not guarantee that all information remains current or complete.

Nothing in this article constitutes an endorsement, recommendation or ranking of any third-party provider. Readers should consult each provider’s official website and conduct their own assessment before making any purchasing decisions.

To request an update or correction, please contact communications@gbg.com

Get in touch with GBG

Request a demo

Capability	GBG	Entrust	Veriff
Biometric deduplication / 1:N face matching	Uses biometric intelligence and identity signals to detect when the same individual appears across multiple onboarding attempts	Known Faces checks whether a face has appeared previously within a defined period	Uses face matching against stored biometric templates to recognize returning users
Multi-account fraud detection	Velocity checks identify when the same verified identity is used repeatedly within a set timeframe	Flags repeated face and document usage	Supports detection of users attempting to create multiple accounts
Liveness detection	Combines biometric verification with advanced passive liveness detection designed to detect presentation attacks, deepfakes, and injected video feeds	Provides automated motion-based liveness checks requiring users to complete simple movements during verification	Uses passive liveness detection models to identify genuine users while detecting masks, screens, and AI-generated selfies