Facebook reveals a recently implemented, sophisticated software detection system designed to target fake accounts on the platform…
Every social media site has a problem with fake accounts. And, Facebook is certainly no exception to this sad reality.
In fact, the company finds and deletes almost as many fake accounts as there are real ones every quarter. Now, the company has pulled back the curtain to reveal a new system that’s working behind the scenes to identify and take down fraudulent profiles.
New Facebook Artificial Intelligence System Deactivates over 100 Million Fake Accounts
Facebook says that it’s using a new machine learning model called “Deep Entity Classification” or DEC. And, it’s already removed more than 100 million bogus accounts from the social site.
What’s more, the company states it’s prevented millions of attempts to create phony accounts before they have a chance to go live. Facebook furthermore says that because of its efforts, such activity has declined since the first quarter of last year. Due to this, it’s limited the number of fakes to about 5 percent of its global monthly active users.
Facebook writes on its Transparency site the following:
“Our goal is to remove as many fake accounts on Facebook as we can. We prioritize enforcement against users and accounts that seek to cause harm and find many of these fake accounts are used in spam campaigns and are financially motivated.
We expect this number to vary over time because of the financial incentives for adversaries to create fake accounts. Our detection technology helps us block millions of attempts to create fake accounts every day and detect millions more often within minutes after creation.”