Microsoft has recently launched a new technology that is more focused to detect ‘deepfakes’, or synthetic media i.e. videos, photos and audios that they are manipulated by artificial techniques. Microsoft deepfake detector tool is named as Video authenticator.
This deepfake detector tool is more focused to detect artificially created or manipulated media such as photos, videos and audio files. Microsoft said that these advanced detection technologies that can be useful in upcoming U.S. elections to help discerning users identify deep fakes.
The tool is named as Microsoft Video Authenticator. This tool can analyse a still photo or video to provide a percentage chance or confidence score to detect that the media is artificially manipulated.
How deepfake detector tool works?
Microsoft’s said that its deepfake detector tool works by detecting the blending boundary of the deepfake and subtle fading or greyscale elements that might not be detectable by the human eye.
The deepfake tool was created using a public dataset from Face Forensic++ and tested on the DeepFake Detection Challenge Dataset. Facebook is also in the competition of creating deepfake detector tool.
Microsoft deepfake detector tool was developed by Microsoft R&D in coordination with Microsoft’s Responsible AI team and the Microsoft AI, Ethics and Effects in Engineering and Research (AETHER) Committee.
In the past, many issues were created by the sharing of fake or manipulated posts. This has caused big issues in the U.S. campaign. The content can be easily manipulated or faked that would be very difficult to detect with the human eye.
This technology has two components, the first tool built into Microsoft Azure that enables a content producer to add digital hashes and certificates to a piece of content. The second is a reader that can be deployed as a browser extension that validates the certificates and matches the hashes and checks whether the content is authentic or has been manipulated.
BBC, CBC/Radio-Canada and the New York Times will test the authenticity of the technology and help to advance the standards that can be adopted.