Intel has developed FakeCatcher, a technology that can detect fake videos with a 96% accuracy rate, returning results in milliseconds.
“Deepfake videos are everywhere now. You have probably already seen them; videos of celebrities doing or saying things they never actually did,” says Ilke Demir, senior staff research scientist in Intel Labs.
Intel’s realtime deepfake detection uses Intel hardware and software and runs on a server and interfaces through a web-based platform.
On the software side, an orchestra of specialist tools form the optimised FakeCatcher architecture.
Teams used OpenVino to run AI models for face and landmark detection algorithms. Computer vision blocks were optimised 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 optimised with Intel Deep Learning Boost and with Intel Advanced Vector Extensions 512, and media blocks were optimised 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 realtime detection platform can run up to 72 different detection streams simultaneously on 3rd Gen Intel Xeon Scalable processors.
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 colour. These blood flow signals are collected from all over the face and algorithms translate these signals into spatiotemporal maps. Then, using deep learning, the system can instantly detect whether a video is real or fake.
Deepfake videos are a growing threat, as companies plan to spend up to $188-billion in cybersecurity solutions, according to Gartner.
It’s also tough to detect these deepfake videos in realtime – detection apps require uploading videos for analysis, then waiting hours for results.
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 organisations could use the detector to avoid inadvertently amplifying manipulated videos. And non-profit organisations could employ the platform to democratise detection of deepfakes for everyone.