Artineh Aladadian
San Francisco, CA — Incode Technologies, a global leader in identity security and fraud prevention, announced the launch of Deepsight, a breakthrough AI defense that detects and blocks deepfakes, injected virtual cameras, and synthetic identity attacks with accuracy.
When Identity Can Be Faked, Everything Breaks
As AI systems increasingly interact and transact autonomously, the ability to instantaneously separate real people from AI-generated fakes becomes critical. Deepsight’s multi-modal AI analyzes video, motion, and depth data to expose inconsistencies that synthetic media cannot reproduce, all in under 100 milliseconds and without adding friction.
“Deepfakes have evolved beyond novelty. They are now a major fraud weapon,” said Ricardo Amper, Founder and CEO of Incode. “When identity can be faked, everything breaks. Deepsight restores trust by ensuring every capture shows a human user in front of the camera, not a deepfake.”
Deepsight anchors Incode’s broader investment in frontier AI research for identity and trust, including Agentic Identity, which connects verified humans to AI agents acting on their behalf.
Three Layers of Defense
Deepsight conducts an assessment of identity across three primary layers, the combination of which can give such specificity to even identify the fingerprint of the generative model used to produce fake content, giving enterprises deeper visibility into the threat.
Behavioral Layer: Spots subtle interaction anomalies from AI bots or fraud farms.
Integrity Layer: Verifies camera and device authenticity to block virtual media.
Perception Layer: Tells apart deepfakes from genuine human users through AI analysis across multiple capture modalities, such as video, motion, and depth.
Proven by Purdue University
Deepsight’s models were benchmarked in Purdue University’s study “Fit for Purpose? Deepfake Detection in the Real World” (October 2025), which evaluated 24 detection systems across commercial, government, and academic providers. Incode achieved the highest accuracy and the lowest false acceptance rate among commercial tools, outperforming both government and academic models.
“We evaluated nine of the most widely used commercial deepfake detection systems and found that Incode’s detector achieved the highest accuracy in identifying fake samples. This outcome suggests that Incode demonstrates stronger robustness and reliability in challenging real-world scenarios”, said Shu Hu, assistant professor at the School of Applied and Creative Computing and the Director of the Purdue Machine Learning and Media Forensics (M2) Lab at Purdue University.
In internal tests, Deepsight was 10 times more accurate than trained human reviewers, confirming that advanced AI defense is now essential to counter advanced AI attacks.
Already Protecting Millions of Users
Deepsight is available now through the Incode Identity Platform, protecting enterprises across KYC onboarding, step-up verification, authentication, workforce access, and age verification.
“AI will change how we live, work, and connect,” added Amper. “Our responsibility is to make sure it does not destroy the trust that holds it all together. Deepsight is how we defend reality itself.”
Deepsight is already being deployed at Scotiabank, Nubank, and, TikTok having protected millions of users across more than 6 million live identity sessions to date.
