Dutch deepfake detection company DuckDuckGoose has reported that one of Latin America’s largest identity and fraud infrastructure providers blocked more than 500,000 AI-generated synthetic identities in the first six months following deployment of DuckDuckGoose’s real-time deepfake detection technology across its onboarding infrastructure.
The unnamed platform serves top-tier banks and fintechs across Brazil and Latin America, processing hundreds of millions of identity verifications annually. Prior to the deployment, synthetic identity attacks had surged more than 350 percent year-over-year on the platform, driven by PIX-enabled real-time payments, high-volume neobank onboarding, and coordinated mule networks that exploit onboarding flows as a primary entry point into financial ecosystems. Traditional KYC controls were performing as designed, but AI-generated synthetic identities were passing them entirely and surfacing downstream as mule accounts and coordinated payment fraud.
DuckDuckGoose’s technology was embedded directly into the platform’s existing onboarding infrastructure without redesigning user flows or adding friction. Detection occurs at the moment of identity establishment, identifying manipulated biometric media before account activation. Existing document verification, biometric matching, and liveness controls remain in place; the deepfake detection layer operates upstream, strengthening trust before the identity enters the system. False rejection rates were maintained below 0.5 percent during the measured period.
The deployment also produced a significant reduction in manual fraud investigations, allowing compliance teams to concentrate resources on genuinely high-risk cases rather than reviewing volume flagged by legacy controls. The region has faced sustained pressure from synthetic fraud actors: researchers previously exposed a dark web operation selling verified digital identities across Latin America, illustrating how the fraud infrastructure operates at an organized scale. The DuckDuckGoose deployment follows a wave of anti-fraud identity verification partnerships across Latin America as financial institutions seek layered defenses against increasingly sophisticated attacks.
“Deepfake identities are no longer failing onboarding. They are completing it,” said Parya Lotfi, CEO of DuckDuckGoose. “By the time manipulation is discovered, those accounts are already active across payments and financial ecosystems. Trust must be established at identity creation. That is the next layer of the identity stack.”
Industry research on classifications of synthetic identities used in fraud has identified the threat as spanning fully synthetic profiles to hybrid combinations of real and fabricated biometrics, making detection at the biometric media layer, rather than document review alone, an increasingly critical control point for onboarding platforms.
Sources: BusinessWire Press Release, Finanznachrichten
–
By the ID Tech Editorial Team
