Facebook Inc removed 2.2 billion fake accounts from its platform in the first quarter of 2019, nearly double the number it had removed in the previous quarter. It had disabled 1.2 billion fake accounts from October-December 2018, according to the latest Community Standards Enforcement Report released last week. This report shares metrics on how Facebook is performing on preventing and removing content that goes against its community standards.

According to the report, the social media platform has seen a steep increase in the creation of abusive, fake accounts on Facebook in the last six months. The company claims that most of these are caught within minutes of registration. However, automated attacks have resulted in more of these accounts making it past the initial detection, which increased prevalence.

Facebook claims that fake accounts represented approximately 5% of their worldwide monthly active users (MAU) on Facebook during Q1 2019 and Q4 2018. “We removed significantly more fake accounts in Q1 2019 and Q4 2018 than in previous quarters, due to an increase in automated, scripted attacks. The majority of these accounts were caught within minutes of registration, before they became a part of our monthly active user (MAU) population," the report said.

The community standards report is one of the steps the company is taking to increase transparency and improve its public image after controversies related to Cambridge Analytica and the platform’s role in spreading fake news and misinformation broke out.

The report also detailed the three ways in which fake accounts are detected and removed.

Blocking accounts from being created: The best way to fight fake accounts is to stop them from getting onto Facebook in the first place by using detection technology that can detect and block accounts even before they are created. Their systems look for a number of different signals that indicate if accounts are created in mass from one location. A simple example is blocking certain IP addresses altogether so that they can’t access our systems and thus can’t create accounts.

Removing accounts when they sign-up: Advanced detection systems also look for potential fake accounts as soon as they sign-up, by spotting signs of malicious behaviour. These systems use a combination of signals such as patterns of using suspicious email addresses, suspicious actions, or other signals previously associated with other fake accounts that have been removed.

Removing accounts already on Facebook: Some accounts may get past the above two defences and still make it onto the platform. Often, this is because they don’t readily show signals of being fake or malicious at first. These accounts are found when their detection systems identify such behaviour or if people using Facebook report them.

Of the accounts that are removed, both at sign-up and those already on the platform, over 99% of these are proactively detected by Facebook before people report them.

The company emphasizes that prevalence of fake accounts is the most important metric and the goal is not only to prevent abuse from fake accounts but also give users the power to share through authentic accounts. Striking the right balance between these goals is crucial.