您现在的位置是：Intel's new deepfake detector can spot a real or fake video based on blood flow in video pixels >>正文

Intel's new deepfake detector can spot a real or fake video based on blood flow in video pixels

后花园论坛社区|2024夜上海论坛网|爱上海419论坛 -- Back garden29人已围观

简介Image: Witthaya Prasongsin / GettyIn recent years, more and more deepfakes have littered the interne...

Image: Witthaya Prasongsin / Getty

In recent years, more and more deepfakes have littered the internet – pieces of synthetic media that take an image or video and use someone else's face or voice to create a new, fake image of people or occurrences. And chances are, you've already seen one and didn't know it was a deepfake.

The very real-looking characteristics of deepfakes have allowed for many instances of misinformation, hoaxes, and fraud to disseminate online. In response, Intel announced a new technology called "FakeCatcher" to detect deepfake media with a 96% accuracy rate.

Artificial Intelligence

AI in 2023: A year of breakthroughs that left no human thing unchanged
These are the jobs most likely to be taken over by AI
AI at the edge: 5G and the Internet of Things see fast times ahead
Almost half of tech executives say their organizations aren't ready for AI or other advanced initiatives

Deepfakes use impressive technology derived from machine learning and artificial intelligence to create scarily accurate impressions of celebrities and politicians doing and saying things they haven't.

Existing technologies can take hours to dispel web surfers' trust in a deepfake, as they use deep learning to investigate signs of digital manipulation.

Also: How to spot a deepfake? One simple trick is all you need

Intel's FakeCatcher can detect a deepfake in real time by "assessing what makes us human – 'blood flow' in the pixels of a video," according to a press release.

Intel says its technology can identify changes in our veins' color when blood circulates through the body. Signals of blood flow are then collected from the face and translated by algorithms to discern if a video is real or a deepfake.