Synthetic identity fraud

Synthetic identity fraud blends real and fake data to create new identities for scams. Learn how it works, why it’s a growing risk, and how to help prevent it.

What is synthetic identity fraud?

Synthetic identity fraud refers to the use of real and fake information to create a new, fraudulent identity for financial gain. Unlike traditional identity theft, where a criminal impersonates an existing person, synthetic identity fraud blends authentic elements such as Social Security numbers with fictitious names, dates of birth, or addresses. These synthetic identities are then used to apply for credit, open bank accounts, or commit large-scale fraud once they build up enough financial credibility.

Because no real person is immediately victimized, synthetic identity fraud often goes undetected for years, and the rise of generative AI and deepfake technology is only making these synthetic personas harder to spot.

How does synthetic identity fraud work?

Identity compilation and manipulation

Criminals compile fragments of both real and fake data—for example, a valid Social Security number belonging to a child or someone with little credit history, paired with an invented name and address. They then manipulate genuine credentials (such as tweaking a birthdate or using a false address) just enough to appear unique while still slipping through traditional verification checks.

The bust-out fraud lifecycle

Many synthetic identities begin with low-value credit applications. After receiving small lines of credit, fraudsters gradually make payments to establish legitimacy. Over time, they leverage these accounts to secure higher credit limits or loans. Finally, the fraudsters perform a “bust-out,” maxing out accounts with no intent to repay, disappearing with substantial financial gains.

AI and deepfake influence

Modern fraud rings are using generative AI to accelerate synthetic identity creation. Deepfake voices, forged documents, and AI-generated profile images make synthetic personas more convincing in digital interactions, customer service calls, and KYC (Know Your Customer) checks. This evolution makes detection even more challenging for financial institutions.

Why is synthetic identity fraud a growing threat?

Scale and statistics

Industry studies estimate synthetic identity fraud accounts for over 80% of new-account fraud. Losses in auto loans alone exceed $1.8 billion annually, with overall costs to banks and lenders topping billions. The crime is attractive to fraudsters because the fabricated identity itself becomes the victim, leaving institutions—not consumers—bearing the brunt of losses.

Detection challenges

Unlike traditional identity theft, there is no individual to file a complaint or dispute charges. Credit histories appear legitimate because fraudsters nurture them over time. Thin credit files, dormant Social Security numbers, and a lack of consistent data-sharing across institutions make synthetic identity fraud incredibly difficult to catch with legacy fraud detection systems.

Who is most at risk from synthetic identity fraud?

Vulnerable data sources

Children’s Social Security numbers are especially attractive because they provide a blank credit slate. Elderly individuals, people who rarely use credit, and deceased individuals also provide fertile ground for identity manipulation.

Impacted institutions

Financial institutions, including banks, credit card issuers, and auto lenders, are attractive targets. Healthcare systems, government programs, and telecom providers are also increasingly targeted as synthetic IDs slip through verification processes.

How can synthetic identity fraud be detected and mitigated?

Beyond traditional checks

Standard identity verification processes, such as matching names to Social Security numbers, often fail to detect synthetic IDs. Fraudsters carefully design personas that can pass these checks.

Advanced fraud detection tools

Financial institutions are turning to advanced analytics, machine learning, and behavioral analysis to flag anomalies across customer interactions. Technologies like voice authentication and device and behavioral analytics offer new layers of defense by identifying fraudulent activity even when the synthetic credentials appear valid on paper.

Industry collaboration

By comparing signals across multiple organizations, detection models can improve, helping to identify synthetic resilience (the ability of synthetic identities to survive repeated checks).

Best practices to mitigate synthetic identity fraud