Inside Facebook's massive cyber-security system 

It took just three years for FIS to evolve from basic beginnings into an all-seeing set of algorithms that monitors every photo posted to the network, every status update– indeed, every click made by every one of the 800 million users. There are more than 25 billion of these "read and write actions" every day. At peak activity the system checks 650,000 actions a second.
t 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.But inside Facebook's network it's much more persuasive. "It's easier to exploit trust relationships in online social networks," says Justin Ma, a computer scientist at the University of California, Berkeley, who develops methods to combat email spam.
Facebook's privacy settings allow users to shield personal information from public view. But because the socialbots posed as friends, they were able to extract some 46,500 email addresses and 14,500 physical addresses from users' profiles– information that could be used to launch phishing attacks or aid in identity theft.A socialbot attack is yet to happen, but it's only a matter of time. Socialbots behave differently to humans that enter Facebook for the first time, in part because they have no real-world friends to connect with, and their random requests lead to an unusually high number of rejections. FIS would be able to use this pattern to recognise and block an attack of socialbots, says Stein. That would put Facebook back on top– if only until hackers release their next innovation.