Cybersecurity researchers in the United Arab Emirates have developed an AI-powered platform to detect deepfakes in images, videos and audio, with the aim of curbing the rapid spread of fake content on social media.
Bashayer Al Salami built a platform called Deepy after his master’s research at Zayed University focused on modern digital threats and how AI-driven manipulation is beginning to outpace what normal users can perceive on their own.
“As AI advances, deepfakes have emerged as one of the most serious digital challenges, allowing images, video and audio to be altered in ways that are not easily detectable by the average viewer,” she said.
Get the latest news. Follow KT on our WhatsApp channel.
Deepy analyzes uploaded files and generates a credibility rating that indicates the likelihood that AI manipulation was used. “We utilize advanced AI algorithms to analyze images, videos, and audio clips, looking for technical indicators within digital files, such as pixel patterns, lighting mismatches, and motion and sound distortion,” Al Salami explained.
The detection itself is based on a set of metrics that humans rarely notice on their own, such as lip movements and facial asymmetries, mismatched lighting and shadow patterns, and subtle distortions at the pixel or frame level. The system also reads digital fingerprints left by image and audio generation algorithms, allowing Deepy to flag manipulation at an early stage using deep learning models trained on thousands of samples of real and fabricated content.
The platform is aimed at government and security agencies, news organizations and journalists, and businesses whose operations depend on verifying digital content. We can also support organizations working on digital security and social media. A version for general users is currently under development. This allows anyone to see your images and videos before sharing them.
Al-Salami said that during times of crisis or political tension, deepfake technology is commonly used to incite fear or sway public opinion, and the circulation of fabricated content increases rapidly. Deepy aims to provide rapid verification so that journalists, public authorities, and ordinary users can inspect material before handing it over.
“The role of technology goes beyond detecting tampering,” she says. “That extends to promoting digital awareness and creating a more reliable and secure media environment in the digital age.”
