FakeCatcher

Intel unveils the ‘World’s First Real-Time Deepfake Detector called ‘FakeCatcher’ which can detect a Deepfake Video in Real Time. Intel’s FakeCatcher deepfake detector analyzes “blood flow” in video pixels to determine a video’s authenticity in milliseconds with 96% accuracy. FakeCatcher is the first deepfake detection algorithm that uses heart rates.

Intel’s FakeCatcher helps restore trust by enabling users to distinguish between real and fake content.

How does it work?

Intel’s FakeCatcher is an AI-based application that helps to detect a Deepfake Video in Real Time, designed by Demir in collaboration with Umur Ciftci from the State University of New York at Binghamton.

FakeCatcher is based on photoplethysmography (PPG), which uses a light source to detect variations in blood circulation, Those PPG signals will be collected from many places on our face and converted into PPG maps and then those PPG maps will be developed into deep-learning approach on top of that to classify into Fake or Real videos. FakeCatcher also uses eye-gaze-based detection to detect deepfake videos in real time.

Intel claims that FakeCatcher is the first real-time deep fake solution platform that has a 96% accuracy and to focus on detection approaches on those like harmful deepfakes they can go up to 72 concurrent detection streams using its latest Generation Xeon Processors.

There are also some responsible deepfakes instead of masking or blurring deepfakes in the digital domain & metaverse are used to mask identity but keep facial expressions exactly the same using synthetic images as source material for the face so, any of the face-recognition algorithms will not be able to recognize that it is a real video.

Intel in its blog post explained how FakeCatcher works as below:

How it Works: Intel’s real-time platform uses FakeCatcher, a detector designed by Demir in collaboration with Umur Ciftci from the State University of New York at Binghamton. Using Intel hardware and software, it runs on a server and interfaces through a web-based platform. On the software side, an orchestra of specialist tools forms the optimized FakeCatcher architecture. Teams used OpenVino™ to run AI models for face and landmark detection algorithms. Computer vision blocks were optimized with Intel® Integrated Performance Primitives (a multi-threaded software library) and OpenCV (a toolkit for processing real-time images and videos), while inference blocks were optimized with Intel® Deep Learning Boost and with Intel® Advanced Vector Extensions 512, and media blocks were optimized with Intel® Advanced Vector Extensions 2. Teams also leaned on the Open Visual Cloud project to provide an integrated software stack for the Intel® Xeon® Scalable processor family. On the hardware side, the real-time detection platform can run up to 72 different detection streams simultaneously on 3rd Gen Intel® Xeon® Scalable processors.

Further added that,

Most deep learning-based detectors look at raw data to try to find signs of inauthenticity and identify what is wrong with a video. In contrast, FakeCatcher looks for authentic clues in real videos, by assessing what makes us human— subtle “blood flow” in the pixels of a video. When our hearts pump blood, our veins change color. These blood flow signals are collected from all over 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.

Deception due to deepfakes can cause harm and result in negative consequences, like diminished trust in media. FakeCatcher helps restore trust by enabling users to distinguish between real and fake content.

There are several potential use cases for FakeCatcher. Social media platforms could leverage the technology to prevent users from uploading harmful deepfake videos. Global news organizations could use the detector to avoid inadvertently amplifying manipulated videos. And nonprofit organizations could employ the platform to democratize the detection of deepfakes for everyone.