Fake videos are a menace. Circulated on social media platforms such as Whatsapp, Facebook and Twitter, they often spread incorrect and false information, damaging reputation and even causing monetary losses for individuals, organisations, and governments. Detecting deepfake videos in real-time is cumbersome as it requires detection apps that upload videos for analysis, and there is a long wait of hours to access the results. But Intel, as a part of Responsible AI work, has productised ‘FakeCatcher’. It is a technology that can detect fake videos with 96% accuracy. The company claims its deepfake detection platform is the world’s first real-time deepfake detector that returns results in milliseconds.
“Deepfake videos are everywhere now. You have probably already seen them; videos of celebrities doing or saying things they never actually did,” says Ilke Demir, senior staff research scientist in Intel Labs. As Deepfake videos are a growing threat, companies will spend up to $188 billion in cybersecurity solutions in the future, according to Gartner.
How it Works:
Most deep learning-based detectors look at raw data to find signs of inauthenticity and identify what is wrong with a video. In contrast, FakeCatcher looks for authentic clues in real videos by assessing what makes us human— subtle “blood flow” in the pixels of a video, says the company. When hearts pump blood, veins change colour. These blood flow signals are collected from all over the face, and algorithms translate these signals into spatiotemporal maps. Then, using deep learning, Intel can instantly detect whether a video is real or fake.
Intel’s real-time platform uses FakeCatcher, a detector designed by Demir in collaboration with Umur Ciftci from the State University of New York at Binghamton. Using Intel hardware and software, it runs on a server and interfaces through a web-based platform.
Where can it be used?
Intel believes there are several potential use cases for FakeCatcher. It can be used by Social media platforms to prevent users from uploading harmful deepfake videos. Even Global news organisations, who are constantly doing fact checks, can use the detector to avoid inadvertently amplifying manipulated videos. And nonprofit organisations could employ the platform to democratise the detection of deepfakes for everyone.
