Latest Intel Deepfake FakeCatcher for Analyzing Cryptic Blood Flow in Videos: Details

FakeCatcher, a real-time deepfake detector, is introduced by Intel. The company claimed that FakeCatcher yields an accuracy of 96 percent. The deepfake detector is expected to work by analyzing the hidden blood flow in video pixels. It is built using Intel hardware and software. FakeCatcher runs on a server while the interaction process takes place through a web-based platform. Elke Demir, a senior research scientist at Intel Labs, along with Omur Sevci of the State University of New York at Binghamton worked together to develop the detector.

Intel It introduced a real-time deepfake detection tool and named it as FakeCatcher. As mentioned earlier, FakeCatcher is expected to detect fakes by analyzing the hidden blood flow in video pixels. This will make it different from other deep learning-based deepfake detectors that look at raw data to try to find signs of inauthenticity and identify what’s wrong with a video.

When our hearts pump blood, our veins change color. These blood flow signals are collected from across the face and algorithms translate these signals into spatiotemporal maps. Then, using deep learning, we can instantly detect whether a video is real or fake,” the company explains how FakeCatcher works in blog post.

The deepfake detector was designed by Demir and Ciftci. Elaborating on the deepfakes issue, Demir said, “Deepfake videos are everywhere now. You’ve probably already seen them. Videos of celebrities doing or saying things they didn’t actually do.”

FakeCatcher is the product of responsible Intel AI work. Intel claims the detector can catch fake videos with an accuracy rate of 96 percent.

Deepfake has been a growing threat since the past few years. study conducted by Forrester Research said in 2020 that costs from deepfake scams would exceed $250 million (roughly Rs. 2,040 crore) that year.