With its size and influence, there is no doubt that Facebook is using some sorts of technology to help it police and manage its vast platforms.
And here, to make the internet safer for everyone, the company announced that it’s open-sourcing two of its technologies, with the aim to help curb the spread of problematic content like child exploitation, terrorist propaganda, or graphic violence online.
Facebook's photo- and video-matching technology have been used to aid the social giant in detecting identical and nearly identical photos and videos in order to remove contents it previously flagged as being in violations of its rules.
By open-sourcing the APIs in question, the company said that developers can create algorithms to match two similar files without the original photo or video.
"Today, we are open-sourcing two technologies that detect identical and nearly identical photos and videos — sharing some of the tech we use to fight abuse on our platform with others who are working to keep the internet safe."
Available on GitHub, the technology creates an efficient way to store files as digital hashes (digital footprints) to determine whether two files are the same or similar.
Making it even more useful, the hashes can also be more easily shared with other companies and non-profits, helping all parties involved to identify harmful contents.
"These technologies are another layer of defense and allow hash-sharing systems to talk to each other, making the systems that much more powerful," said Facebook.
"Our photo-matching algorithm, PDQ, owes much inspiration to pHash although was built from the ground up as a distinct algorithm with independent software implementation. The video-matching technology, TMK+PDQF, was developed together by Facebook’s Artificial Intelligence Research team and academics from the University of Modena and Reggio Emilia in Italy," continued Facebook.
Facebook has contributed many open-source projects in the past, but "this is the first time we’ve shared any photo- or video-matching technology."
Facebook designed these technologies in conjunction with Facebook AI Research ('FAIR'), and based on its experience detecting abuse across billions of posts on its platforms.
This contribution follows previous projects, like Microsoft’s PhotoDNA, which is meant to fight child exploitation, and Google Content Safety API.
"Today’s announcement also is part of an industry-wide commitment to building a safer internet," said Facebook.
In the technologies' use cases, Facebook gave an example of terrorist propaganda on its platforms. The social giant was able to remove the contents and hash them using a variety of techniques, including using these tools the company is open-sourcing.