FACEBOOK has released details of the extraordinary security infrastructure it uses to fight off spam and other cyber-scams.
Known as the Facebook Immune System (FIS), the massive defence network appears to be successful: numbers released by the company this week show that less than 1 per cent of users experience spam. Yet it's not perfect. Researchers have built a novel attack that evaded the cyber-defences and extracted private material from real users' Facebook accounts.
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 actually a pretty impressive achievement that tackles the spam problem proactively in comparison to Google's largely reactive struggle against spam (although IMO Panda and similar stuff represents somewhat of a shift on that front for Google).
Facebook said this week that, thanks to FIS, less than 4 per cent of the network's messages are spam and that fewer than 1 in 200 users experience spam on any given day.
Those are pretty nice numbers - you reckon any search engine could match them?
I'm definitely impressed by Facebook's "FIS" system. I remember a couple of years ago I used to get a lot of spam via facebook but now-a-days, I rarely see anything. When something does get through, they're pretty quick to react to it.