<img loading="lazy" src="http://www.newscientist.com/data/images/ns/cms/dn21095/dn21095-2_300.webp" align="right" hspace="15" vspace="5" />
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.


"It's a big challenge," says Jim Larus, a Microsoft researcher in Redmond, Washington, who studies large networks. The only network bigger, Larus suspects, is the web itself. That makes Facebook's defence system one of the largest in existence.


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.


One notable attack took place in April, says <a href="http://research.microsoft.com/en-us/projects/ldg/a10-stein.pdf" target="_blank" class="news_link" title="Facebook Immune System">Tao Stein</a>, a Facebook engineer who works on the system. It began when several users were duped into copying computer code into their browser's address bar. 



<a href="http://www.newscientist.com/article/dn21095-inside-facebooks-massive-cybersecurity-system.html" target="_blank" class="news_link" title="Source">Continue reading at NewScientist.com</a>

Inside Facebook's massive cyber-security system