Technology company Intel launched world’s first deepfake detector platform on November 14 named as FakeCatcher. According to the company, FakeCatcher can detect deepfake videos in milliseconds with about 96 percent of accuracy rate.
“Deepfake videos are everywhere now. You have probably already seen them; videos of celebrities doing or saying things they never actually did.” said Ilke Demir, Senior staff research scientist, Intel Labs.
What is a Deepfake
In simple words, Deepfake is a technology that can replace one’s face or body with another person’s face or body and mimics every action as well. And it appears that someone else is doing or speaking something. This technology can be used to spread false information on the internet.
However, Deepfake technology can be helpful in some ways. For instance, Bruce Willis has sold his face rights to a Deepfake firm Deepcake. And he is excited about this technology saying that he can participate in filming, even if he is on another continent. Talking about the dark side of this technology Deepfake can harm or mislead people. This will ultimately result is decreased trust in the media.
Moreover to detect deepfake videos is very difficult these days. As the apps takes longer time to upload videos for analysis and can take several hours for results.
Intel’s FakeCatcher Working
The FakeCatcher runs on a server that uses Intel software and hardware. Moreover, it interfaces through a web based platform. Talking about the software side of the FakeCatcher, there is a combination of specialist tools. And for the hardware part there are 72 different detection streams runs simultaneously in real-time on 3rd gen Intel Xeon Scalable processors.
“Unlike, Most of the deep learning-based detectors, which look at raw data to try to find signs of inauthenticity and identify what is wrong with a video. FakeCatcher looks for authentic clues in real videos. It assesses what makes us human – subtle blood flow in the pixels of a video. These blood flow signals are collected from all over the face and algorithms translate these signals into spatiotemporal maps. Then, using deep learning, it can instantly detect whether a video is real or fake.” Intel said in a statement.
FakeCatcher : A helpful Deepfake detector Tech
Further it can be said that this technology will help people in identifying deepfake videos in time. And this will ultimately stop the spread of misinformation. Furthermore, social media platforms can use this tech to prevent the upload of harmful deepfake contents. And last but not the least, various news agencies can use FakeCatcher to determine whether the video is fake or not without spending lot of time.