[ad_1]
Intel has been a technological powerhouse and continues to be a force to be reckoned with. But the company has clearly been over chips in the past few years, using its capabilities to tackle various issues. And now, Intel claims to have built a detector that will tell you if a video contains deepfakes with 96 percent accuracy.
The company says FakeCatcher is the world’s first real-time deepfake detector. Intel used its hardware and software prowess to design this system, in partnership with public university researchers.
Intel designed FakeCatcher in its labs with a senior staff research scientist, Ilke Demir working in collaboration with Umur Ciftci of the State University of New York. FakeCatcher runs on a server built by Intel using its own hardware and software. The application provides data through a web-based interface. “Deepfake videos are everywhere now. You’ve probably already seen them. Videos of celebrities doing or saying things they never actually did.” Demir says in this Mail.
Deepfakes are basically content where one person appears in the image but the person speaking is someone else. Think of it as a virtual facelift being performed which is unrecognizable to the average person.
Intel FakeCatcher Deepfake Detector: How It Works
Intel says FakeCatcher is unlike any other deepfake detector on the market. The claim is long and says that the technology used to detect videos helps the company provide an accuracy of 96 percent, which is as close as anyone can get to a perfect match.
Intel says FakeCatcher works by analyzing the blood flow in video pixels. This is accomplished using a technique called photoplethysmography, or PPG. With PPG, Intel technology is able to measure the amount of light that is reflected off living tissue. Now, if someone in the video is real, PPG will work normally, but if it’s a deep fake, the detector will alert the person.
The company also talks about the fact that when your heart is pumping blood, the vein changes color, which is easily detected by a FakeCatcher to alert the person or platform.
Intel thinks it has found a solution using a feature that no one else has used yet. The company hopes that social media platforms can use its technology to detect and remove fake content before mass consumption.
Deepfakes are hard to spot, forcing companies to invest millions in technology that may or may not deliver results. But Intel is clearly working on something unique and hopefully it will be put to good use in the near future.
Read all files The latest technology news over here
[ad_2]
Source link
