LONDON, July 22, 2025 (GLOBE NEWSWIRE) — FACIA, a global leader in facial biometric technology, announced that its deepfake detection system has achieved 100% accuracy on multiple industry datasets, including Meta’s Deepfake Detection Challenge Dataset (DFDC). FACIA’s proprietary algorithm was tested across more than 100,000 images and videos, reporting an overall detection accuracy of 99.6%.
The announcement comes amid growing global concern over synthetic media. In 2023 alone, the number of deepfake videos tripled, with total deepfake content increasing eightfold. These manipulated assets are now widely used in fraud schemes, misinformation campaigns, and non-consensual content creation, prompting regulatory responses worldwide.
FACIA’s model delivered perfect classification on the DFDC dataset, which includes 2,100 manipulated videos using eight different facial alteration techniques. Additional testing was conducted on FACIA’s internal dataset of 3,430 AI-generated images created using tools like Midjourney, Artbreeder, and Leonardo.ai, achieving 89.01% accuracy.
Further tests on four leading open-source deepfake datasets contributed to the model’s combined detection accuracy of 99.6%. FACIA highlighted the system’s performance across varying conditions, noting its relevance to sectors like finance, defense, and immigration.
“This isn’t just about setting a benchmark,” said Daniyal Assad Chughtai, CTO at FACIA. “The rate at which deepfakes are spreading makes real-time, scalable detection infrastructure a critical need for social platforms, financial services, and public agencies.”
FACIA’s system differs from many current solutions by moving beyond frame-by-frame analysis and passive liveness detection. Instead, it uses a multi-layered detection pipeline specifically built to counter modern deepfake threats. The company also maintains low false acceptance and rejection rates, essential for high-assurance identity applications.
Looking ahead, FACIA plans to expand its detection capabilities with multilingual spoof detection, broader dataset training, and enhanced API support for integration into third-party platforms.
The announcement arrives as major platforms like Meta, TikTok, and X (formerly Twitter) face mounting scrutiny over synthetic media and misinformation.
FACIA is currently offering live demonstrations of its technology to partners and customers in deepfake-vulnerable sectors.
About FACIA
Facia provides deepfake prevention and detection solutions across 190+ countries. Its offerings include 3D liveness detection, age estimation, and iris recognition, built with some of the market’s fastest, most accurate algorithms.
Media Contact
Ans Abbas
Marketing Lead | Facia
ans@facia.ai
A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/03d892c2-4376-49ed-bf15-ae7ec3717161
Nguồn: GLOBENEWSWIRE – Đơn vị phát hành hoàn toàn chịu trách nhiệm về nội dung thông báo này.
