Facebook developed an AI-based technology that can detect the origin of deepfakes.
Facebook recently developed an AI-based technology that can reverse-engineer deepfakes and can detect the origin of deepfakes as well.
In a blog post, Facebook said that its AI-based technology can actually track the origin of deepfakes by finding unique characteristics that might help it identify the source of a deepfake meant to spread misinformation.
Seeing the company at the forefront of fighting against deepfakes was actually refreshing as deepfakes would largely spread through social media platforms — including Facebook, WhatsApp, Messenger, and Instagram.
Facebook teamed up with Michigan State University in order to create technology that can detect whether an image or a video was a deepfake or a genuine.
READ ALSO: Facebook Set To Launch Its Own Podcast Platform
Facebook used its own AI in order to look for clues that indicated an image or a video was doctored.
The same technology can also be used to identify commonalities between deepfakes and to create a fingerprint that might identify the origin of the malicious deepfake.
While social media attackers could attempt to hide their tracks when making malicious deepfakes for malicious purposes, the company’s AI could still pick up fingerprinting elements that might allow investigators to determine the origin of deepfakes.
Facebook was still perfecting its technology for detecting deepfakes, but said “this work will give researchers and practitioners tools to better investigate incidents of coordinated disinformation using deepfakes, as well as open up new directions for future research.”
For more information about this, you may visit Facebook’s full blog here.
For more news and updates, you may feel free to visit this site more often. You may also visit Newspapers.ph via our official Facebook page and YouTube channel.
