Incode Technologies, a global leader in identity security and fraud prevention, has launched Deepsight, an AI defense system designed to detect and block deepfakes, injected virtual cameras, and synthetic identity attacks with high accuracy. This new technology aims to counter the increasing sophistication of AI-generated fakes in autonomous interactions and transactions.
Deepsight’s multi-modal AI analyzes video, motion, and depth data to identify inconsistencies that synthetic media cannot replicate. The system operates in under 100 milliseconds and is designed to integrate without adding friction to existing processes.
Ricardo Amper, Founder and CEO of Incode, stated that deepfakes have evolved into a significant fraud weapon, threatening the integrity of identity verification. He emphasized that Deepsight restores trust by confirming the presence of a human user in front of the camera, rather than a deepfake. Deepsight is part of Incode’s broader investment in frontier AI research for identity and trust, which includes Agentic Identity, a system connecting verified humans to AI agents operating on their behalf.
Deepsight performs identity assessments across three layers to provide detailed threat visibility, including the ability to identify the generative model used to produce fake content. The Behavioral Layer detects subtle interaction anomalies from AI bots or fraud farms. The Integrity Layer verifies camera and device authenticity to block virtual media. The Perception Layer distinguishes deepfakes from genuine human users through AI analysis across multiple capture modalities, such as video, motion, and depth.
Roman Karachinsky, Chief Product Officer at Incode, noted that determining the authenticity of an individual is becoming a critical challenge. He added that Deepsight has demonstrated its effectiveness in both controlled lab environments and real-world applications.
Deepsight’s models were benchmarked in Purdue University’s October 2025 study, “Fit for Purpose? Deepfake Detection in the Real World.” This study evaluated 24 detection systems from commercial, government, and academic providers. Incode achieved the highest accuracy and the lowest false acceptance rate among commercial tools, surpassing both government and academic models.
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, confirmed Incode’s strong performance. According to Hu, Incode’s detector achieved the highest accuracy in identifying fake samples among nine widely used commercial deepfake detection systems, indicating its robustness and reliability in challenging real-world scenarios. In internal tests, Deepsight was found to be 10 times more accurate than trained human reviewers.
Experian, a global data and technology company, collaborates with Incode to integrate AI-powered identity verification and Deepsight’s deepfake detection into its identity and fraud solutions. Keir Breitenfeld, Senior Vice President of Fraud and Identity at Experian, cited Experian’s 2025 Identity and Fraud report, which indicates that 72% of business leaders anticipate AI-generated fraud, including deepfakes, will be a primary operational challenge by 2026. He stated that the partnership equips clients with leading protection against AI-powered attacks.
Deepsight is currently available through the Incode Identity Platform, offering protection for enterprises in areas such as Know Your Customer (KYC) onboarding, step-up verification, authentication, workforce access, and age verification. Amper commented on the transformative potential of AI, emphasizing the responsibility to safeguard the trust fundamental to its operation, positioning Deepsight as a defense against manipulated reality.
The technology is already deployed at companies including TikTok, Scotiabank, and Nubank, having protected millions of users across more than six million live identity sessions to date.
Incode Technologies is a global leader in trust and identity, powering major U.
S. banks, telecom providers, fintechs, marketplaces, and governments worldwide, processing over four billion identity checks annually across multiple industries.
