Intel’s ‘FakeCatcher’ can detect deep fakes with 96% accuracy

The FakeCatcher deep faux detector works by analyzing the ‘blood movement’ within the video pixels to find out the authenticity of a video in milliseconds (Picture: Intel)

Intel has developed know-how that may efficiently distinguish between actual movies and movies. deep scams in real time using skin analysis.

Its new technology, FakeCatcher, can detect fake videos with 96% accuracy and is the “world’s first real-time deep fake detector” that returns results in milliseconds.

“Deepfake videos are everywhere now. You’ve probably seen them already,” says Intel Labs Senior Staff Research Scientist İlke Demir, “Videos of celebrities doing or saying things they’ve never actually done.

The FakeCatcher deepfake detector works by analyzing the ‘blood flow’ in the video pixels to determine the authenticity of a video in milliseconds.

Most deep learning-based sensors look at raw data to try to find signs of non-authenticity and determine what’s wrong with a video. Rather, FakeCatcher looks for authentic clues in real videos by assessing what makes us human, such as the ‘blood flow’ in a video’s pixels.

To view this video, please enable JavaScript and consider switching to a web browser that supports HTML5 video

Our veins change color as our heart pumps blood. These blood flow signals are collected from all over the face, and algorithms turn these signals into maps.

“We can then instantly detect whether a video is real or fake using deep learning,” Intel said.

According to the company, up to 72 streams can be analyzed simultaneously using one of the 3rd Gen Xeon processors. But these processors are slightly heavier than the CPUs found in our laptops and desktops and can cost up to around £4,000.

Deepfake videos are a growing threat, costing companies $188 billion in cybersecurity solutions, according to Gartner.

These deepfake videos are also difficult to detect in real time, as detection apps require uploading videos for analysis and then waiting hours for results.

What are deepfakes?

Deepfakes are videos and images that use deep learning AI to fake something that isn’t actually there. They are best known for their use in porn videos, fake news, and hoaxes.

Disinformation can be used to portray events that never happened as real, to put people in certain situations they’ve never been in, or to portray people saying things they never said.

First of all, deep frauds may be responsible for the loss of trust in the media.

In April, Ukraine accused Russia of preparing to launch a ‘deep fake’ in which President Volodymr Zelensky surrendered.

FakeCatcher can help restore trust by enabling users to distinguish between real and fake content.

Ukraine accused Russia of preparing to launch a ‘deepfake’ in which President Volodymr Zelensky surrendered (Image: Twitter

Social media platforms can leverage know-how to stop customers from importing dangerous deep faux movies.

The know-how can be used to stop unintended magnification of movies which were manipulated by information organizations. Nonprofits can use the platform to democratize deep fraud detection for everybody.

MORE : Deepfake porn ruins lives – however as one lady found, it solely takes 8 seconds to render a picture.

MORE INFO: It seems that Bruce Willis didn’t promote his digital rights to Deepfake.

About the author


Leave a Comment