Fed up with losing email to your spam folder? Gmail’s artificial intelligence wants to help

Google arms bulk senders with spam smarts in Gmail Postmaster Tools.
No matter how hard Google tries to keep important stuff in our Gmail inboxes and garbage filtered away into our spam folders, we still end up dumpster-diving into that spam folder to find missing email.
Well, we should be taking fewer and fewer of those dives, thanks to Google having smartened up its spam filters and having launched what it's calling Gmail Postmaster Tools, the company said on Thursday.
These are tools for qualified senders of high-volume email: the senders who send out large amounts of non-spammy email, such as banks or airlines that send monthly statements or ticket receipts.
Sometimes these innocent, desirable emails mistakenly get lumped in with the seedier inhabitants of email land, and thus do they wind up in the spam folder and force us to go picking through the garbage to find them.
The new tools will help such high-volume senders analyze their email, Google says, including data on delivery errors, spam reports, and reputation:
This way they can diagnose any hiccups, study best practices, and help Gmail route their messages to the right place.
As far as getting smarter about accurately identifying spam goes, Google's been using machine learning to improve its spam filters from the get-go.
Every time we click "Report spam" or "Not spam", the spam filters get a little bit smarter about what we want and don't want in our inboxes.
Google says it's now also bringing the same intelligence of its Google Search and Google Now services to its spam filters in a number of ways that should help identify the truly spammy and weed out the truly phishy.
From its announcement:
  • For starters, the spam filter now uses a neural network to detect and block the especially sneaky spam—the kind that could actually pass for wanted mail.
  • Google says it also recognizes that not all inboxes are alike. So while your neighbor may love weekly email newsletters, you may loathe them. With advances in machine learning, the spam filter can now reflect these individual preferences.
  • Finally, Google says the spam filter is better than ever at rooting out email impersonation - what it calls "that nasty source" of most phishing scams. Thanks to new machine learning signals, Gmail can now figure out whether a message actually came from its sender, and thus keep bogus email at bay.
These are glad tidings. At Naked Security, we're always warning people to stay alert to phishing attempts by:
  • being wary when it comes to unsolicited email;
  • never clicking on links in unsolicited email; and
  • never opening attachments in unsolicited email.
But things can and do get a lot stickier in real life.
We open unsolicited email all the time, which is why we should of course learn to recognize the overt signs of a scam email - i.e., poor spelling and grammar, suspicious senders, uncommon requests, terrible formatting, bogus links, and more.
Naked Security's John Shier dove into just how tricky it can be to discern if an email is real or a scam.
Being able to discern the difference is important, given that cyber crooks doggedly attack us on a daily basis, be it via phishing email or phishing sites.
After all, as Google found in a study last autumn, phishing may sound old school, but it's alive and well, with some masterpieces of phishery being so convincing that they work on an eye-popping 45% of visitors.
So good on Google for throwing its machine learning at this continuing security threat.
Thankfully, its postmaster tools are only available to qualified senders who meet its reputation requirement: no spammers or phishers allowed.
So tough luck, guys: you're on your own when it comes to trying to contact us about that Nigerian prince's inheritance.

Comments

Popular posts from this blog

Underground DLC: Procedurally generated levels come to The Division

United Airlines CEO explains why the Boeing 747 jumbo jet will soon go away

Former US Secret Service agent may have stolen bitcoins