Intel’s FakeCatcher can detect fake videos with 96% accuracy

representative image

Photo: IANS

Amid the growing threat of misinformation, Intel has unveiled a new deepfake detection platform that can flag discrepancies with 96 percent accuracy. The platform is the world’s first real-time deepfake detector that returns results within milliseconds.

What is a Deep Fake?

Deepfakes — a combination of the words “deep learning” and “fake” — are visual media in which an existing image or video of a person is replaced with a likeness of another. The technology uses machine learning and artificial intelligence to create deceptive (yet real) content. Deepfakes have drawn attention in recent years for their potential use in pornographic material, fake news, financial fraud, and more.

how false catcher Work?

According to the company, the Intel technology looks for real clues in real video by evaluating subtle “blood flow” in video pixels.

“When our heart pumps blood, our veins change color. These blood flow signals are collected from all over the face, and an algorithm converts these signals into a spatiotemporal map. Then, using deep learning, we can instantly detect that the video is real.” or fake,” the company said in a press release earlier this month.

How to take advantage of this technology?

FakeCatcher has several potential uses. As Intel’s press release reminds, social media platforms could leverage the technology to prevent users from uploading harmful deepfake videos. Meanwhile, news organizations around the world could use detectors to avoid inadvertently amplifying manipulated videos.

Source link