Incode Deepsight wins the 2026 Award for Best AI-Driven Innovation in the Datos Impact Awards in Fraud & AML
Datos Insights recognizes Deepsight, Incode's multimodal deepfake detection module, for a three-layer architecture attackers have to beat all at once.
SAN FRANCISCO, 9 September, 2026 - Incode, a leading platform of AI-powered identity verification and fraud prevention, today announced it has won the 2026 Award for Best AI-Driven Innovation in the Financial Crime Convergence Innovation Category of the Datos Impact Awards in Fraud & AML. The award recognizes Incode Deepsight, the company's multimodal deepfake detection module. Datos Insights analysts and practitioners from financial institutions judged the category.
The recognition lands on a market that has changed underneath its own defenses. AI-assisted fraud sessions on Incode's platform grew from 2% in Q1 2023 to 32% in early 2026, and Incode projects 65% by the end of this year. Over the same period, the cost of producing a convincing deepfake collapsed from roughly US$1,000 in 2020 to US$1 today, and production time fell to 18 seconds. Detection built on the old economics fails against that math.
Incode built Deepsight for exactly that. Every session passes through three independent layers. The perception layer detects deepfakes with multimodal AI that reads RGB, depth, and motion signals for the cross-modal inconsistencies generative tools leave behind. The behavioral layer flags bot-like patterns and farm-style automation. The integrity layer blocks tampered devices, emulators, and virtual cameras attempting to inject manipulated content at the moment of capture. On documents, a domain-specific vision language model reasons jointly about layout, text, metadata, and pixel-level artifacts, producing explainable fraud decisions. Deepsight fuses the layers into a single decision, so an attacker who defeats one still faces the rest.
"Datos Insights analysts who cover fraud and AML end to end judged this category, alongside practitioners from the financial institutions that carry the losses when detection fails. Recognition from that room means more than any claim we could make about ourselves," said Ricardo Amper, Founder and CEO of Incode.
Independent testing points the same way. In a Purdue University benchmark built on real-world deepfake incidents circulating on social media, Deepsight delivered the lowest false acceptance rate on images of any tool evaluated (2.56%) and the highest video accuracy among commercial tools (77.27%). In identity verification specifically, Incode's testing across millions of real sessions shows a false acceptance rate 68x lower than the next-best commercial solution, and detection 10x better than expert human reviewers.
Across the full module, Deepsight reports a 0.4% false positive rate and a 0.5% false negative rate, with a 0.04% false rejection rate on genuine documents. The document vision language model delivers an 8.8x improvement in AI-generated document detection over traditional machine learning and needs as few as five samples to cover a new document type, which is how Deepsight adapts to a newly released fraud tool in weeks rather than quarters. Twice a year, Incode runs a spoof bounty program through HackerOne that draws roughly 1,500 bypass attempts from ethical hackers, and every finding feeds model retraining.
In its award profile, Datos Insights credited Incode's exclusive government biometric data rights, continuous adversarial testing, and zero third-party machine learning dependencies, writing that the combination "creates a detection posture that is hard to replicate."
Client deployments across telecommunications, banking, fintech, gaming, and social media report a 38% fraud reduction at a fintech that displaced an incumbent after a six-month head-to-head evaluation, and 100% compliance with the EU Digital Services Act, U.K. Online Safety Act, and U.S. state age-verification mandates at a gaming client.
Datos Insights' annual awards program recognizes innovations leading the industry and pioneering new and disruptive financial crime products and capabilities.
About Incode
Incode is a global leader in AI-driven identity and trust, with a mission to power a world of trust. The platform verifies identity and age, stops fraud, and turns verification into business enablement. Incode builds its own frontier models, adapting to any new fraud while letting good users through, trained on one of the industry's largest identity datasets: 7 billion+ trust checks and 400 million+ profiles worldwide, on a privacy-by-design architecture. Incode's customers include eight of the top 10 U.S. banks, eight of the top nine U.S. telcos, three of the top three global neobanks, and four of the top five global marketplaces. Founded in 2015 in San Francisco, Incode is a team of 600+ across 25+ nationalities.
About Datos Insights
Datos Insights is the leading research and advisory partner to the banking, insurance, and securities industries, both the financial services firms and the technology providers who serve them. In an era of rapid change, Datos Insights empowers firms across the financial services ecosystem to make high-stakes decisions with confidence and speed. Its distinctive combination of proprietary data, analytics, and deep practitioner expertise provides actionable insights that enable clients to accelerate critical initiatives, inspire decisive action, and de-risk strategic investments. Visit datos-insights.com to learn more.