gabrielle_cc / Pixabay
We know how Gmail blocks emails it thinks are spammy, right? And it’s getting better at it. How? Google itself today provided the answer.
It said on its official blog that using open-source software TensorFlow, it was able to halt an additional 100 million Gmail spam messages. Every day. Considering the fact that 1.5 billion & 5 million paying businesses use Gmail, that’s one hell of a statistic.
It uses its existing machine learning (ML) models with TensorFlow to refine filter models further, while allowing the Gmail team to focus less on the underlying ML framework, & more on solving the problem: ridding your Inbox of Gmail spam.
Here’s what Google has said:
We’re now blocking spam categories that used to be very hard to detect. Using TensorFlow has helped us block image-based messages, emails with hidden embedded content, and messages from newly created domains that try to hide a low volume of spammy messages within legitimate traffic.
ensorFlow helps us catch the spammers who slip through that less than 0.1 percent, without accidentally blocking messages that are important to users.
One person’s spam is another person’s treasure
ML makes catching spam possible by helping us identify patterns in large data sets that humans who create the rules might not catch; it makes it easy for us to adapt quickly to ever-changing spam attempts.
ML-based protections help us make granular decisions based on many different factors. Consider that every email has thousands of potential signals. Just because some of an email’s characteristics match up to those commonly considered “spammy,” doesn’t necessarily mean it’s spam. ML allows us to look at all of these signals together to make a determination.
Finally, it also helps us personalize our spam protections to each user—what one person considers spam another person might consider an important message (think newsletter subscriptions or regular email notifications from an application).
For more, click here.
