The best defence is to verify genuine presence at onboarding, not after account creation. Financial institutions should combine biometric face verification with liveness detection so the system checks whether the person is real, live, and present in real time. That approach is stronger than passwords, OTPs, or device checks because synthetic identities often pass those controls while still being fabricated.
Why synthetic identity fraud has to be stopped at onboarding
Synthetic identity fraud is most dangerous before an account exists, because once a fabricated profile is accepted, it can age, build trust signals, and later be used for bust-out or other fraud. The onboarding decision is therefore the control point that matters most. If the institution cannot tell whether the applicant is a real person present in real time, downstream fraud controls start too late.
That is why identity proofing needs to focus on presence, not just data consistency. Synthetic identities can look plausible across bureau data, phone records, email age, and device attributes, so a strong onboarding control has to verify that a live human is actually submitting the application and not a replayed image, injected video, or other fabricated presentation.
For financial institutions, the core issue is not simply fraud detection, but assurance. The institution is deciding whether to create a new customer relationship, so the proofing step must establish enough confidence to bind the account to a real applicant before any credential, funding path, or transaction capability is issued.
Why biometric face verification and liveness detection work better than passive checks
Face verification becomes useful when it is paired with liveness detection, because the system is then testing both identity claim and live presence. That combination is materially stronger than passwords, OTPs, or device checks alone, since those controls can authenticate access to a channel without proving that the applicant is a real person standing there at onboarding.
The practical advantage is that liveness detection raises the cost of presentation attacks, including printed images, screen replays, camera injection, and deepfake-assisted submissions. Face verification confirms that the face matches the claimed identity, while liveness checks reduce the chance that a synthetic or manipulated presentation is accepted as genuine.
Used properly, these controls should be part of a broader proofing flow, not a standalone decision. Institutions should treat them as one signal in an onboarding risk decision that also considers document authenticity, application consistency, and high-risk pattern review. The point is to make fabricated identities fail early, before they gain account history or financial utility.
Where onboarding controls fail in practice
Onboarding controls fail when they are designed to recognise a legitimate-looking application rather than a real applicant. Synthetic identity fraud often succeeds because the institution overweights static data, such as identity records or contact details, and underweights whether the applicant is physically and temporally present during proofing.
Another common failure is assuming that stronger login controls will compensate later. They will not, if the account was opened fraudulently in the first place. Once a synthetic identity is onboarded, the institution may be protecting a fraudulent customer profile with very effective security controls.
Identity Proofing and KYC Guide is useful here because it covers assurance levels, document checks, liveness, and the account-opening fraud paths that matter in this decision.
Synthetic Identity Fraud Guide deepens the specific fraud patterns behind fabricated identities, including onboarding signals and how they differ from ordinary identity theft.
Financial Services Identity Security Guide is also relevant because financial institutions need to align onboarding assurance with broader regulatory and access-risk expectations.
Risk and Threat Considerations
Synthetic identity fraud is a front-door risk with long-tail impact. If a fabricated identity is accepted at onboarding, the institution may inherit losses much later, after the profile has built creditworthiness, transaction history, or internal trust. The attacker’s objective is to make the account look legitimate long enough to monetize it.
Failure mechanism: Weak onboarding checks validate data coherence but do not prove live presence, so replayed media, injected video, or deepfake-assisted enrolment can pass as a real applicant and create a durable fraudulent customer record.
Impact: The institution may issue an account to a fake identity, creating exposure to bust-out fraud, fraudulent credit use, mule activity, recovery abuse, and costly remediation after the customer profile has already been trusted.
Standards & Framework Alignment
This section maps relevant standards and security frameworks to the operational risks and controls described in this guidance.
NIST SP 800-63, OWASP ASVS, NIST SP 800-53 Rev 5 and CIS Controls v8 set the technical controls, while PCI DSS v4.0 defines the regulatory obligations.
| Framework | Control / Reference | Relevance |
|---|---|---|
| NIST SP 800-63 | IA-5 — Authenticator Management | Synthetic onboarding relies on strong identity proofing and authenticator binding. |
| Recommendation — Require liveness-backed proofing before issuing account credentials or recovery paths. | ||
| OWASP ASVS | V6 — Authentication | Face verification with liveness strengthens assurance at account enrolment. |
| Recommendation — Verify onboarding authentication flows resist replay, spoofing, and enrolment abuse. | ||
| NIST SP 800-53 Rev 5 | IA-8 — Identification and Authentication (Non-Organizational Users) | Banks must prove external applicants are real before opening an account. |
| Recommendation — Use strong proofing and authentication controls for customer onboarding. | ||
| CIS Controls v8 | CIS-5 — Account Management | Prevent fraudulent account creation by tightening lifecycle controls at onboarding. |
| Recommendation — Enforce account approval checks that block fraudulent registrations before activation. | ||
| PCI DSS v4.0 | 8.3 — Strong Authentication for Access into the Cardholder Data Environment | Financial onboarding commonly intersects with identity assurance and strong authentication. |
| Recommendation — Apply strong authentication wherever onboarding grants access to sensitive financial systems. | ||
Practitioner Guidance
What to prioritise: Put the strongest proofing step at the first account-opening decision, not after account creation or after funding. If the control cannot reliably distinguish a live applicant from a fabricated presentation, treat the onboarding path as high risk.
What to verify: Confirm that the face-check flow includes active or passive liveness testing with resistance to replay and injection, and that failed attempts, edge cases, and exception handling are reviewed by fraud operations rather than auto-approved.
Decision rule: If the institution cannot establish real presence with enough confidence, do not open the account on the strength of device reputation, OTP success, or static identity data alone. Those signals can support the decision, but they should not replace proof of a live applicant.
Practitioner takeaway: The best control is the one that forces synthetic identities to fail before they become customers, because every later safeguard is more expensive and less decisive once the account already exists.
Related resources from NHI Mgmt Group
- How should financial institutions design fraud controls for AI-enabled synthetic identity and account takeover attacks?
- How can financial institutions detect APP fraud before money leaves the account?
- How should financial institutions defend against synthetic identity and deepfake-driven fraud in APAC onboarding flows?
- How should financial institutions implement remote identity verification without increasing fraud risk during digital onboarding and account recovery?
Deepen Your Knowledge
Free weekly newsletter
Subscribe to the NHI & AI Identity Journal
The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.
Bonus 33% off our NHI Course when you subscribe.
Reviewed and updated by the NHIMG editorial team on November 4, 2026.
NHI Mgmt Group — the #1 independent authority on Non-Human Identity, IAM, and Agentic AI security. nhimg.org