Facebook’s cyber-security system processes and checks 650,000 actions every second to keep its users safe from spam and cyber-attacks on the social network.

This fact is one of a number of details that the company has released about the system, called The Facebook Immunity System (FIS). Results have shown that it is highly efficient too, with just 1% of users reporting issues around spam.

FIS was developed over a three year period and is robust enough to handle the estimated 25 billion actions that are made by the social networks 800 million plus users every day. According to Facebook, the system has seen spam drop to account for less than 4 per cent of its total messages affecting less than 0.5 percent of its users.

Details of how the system works come from The New Scientist:

It protects against scams by harnessing artificially intelligent software to detect suspicious patterns of behaviour. The system is overseen by a team of 30 people, but it can learn in real time and is able to take action without checking with a human supervisor.

The FIS is also backed up by a team of 30 security experts, each of whom helps hunt for spam across the network leaving no status update, like, share or comment unturned.

Despite the technology, users should be aware of the growing threat of “socialbots”, fake users which look and behave like ordinary people on Facebook. Socialbots issue a high numbers of friend requests as they attempt to friend users to get access to personal information that could be used for phishing, identity fraud or other schemes.

Data from the social network suggests that as many as 20 percent of those targeted by socialbots accept such requests, putting their information and themselves at risk.

Socialbots are difficult to detect, even for the FIR, but those behind the system are working to cover the threat. Even though Facebook is doing big things to keep its site safe, users should remain vigilante and careful of links and suspicious behaviour.