Where did we find these 100 million extra spam messages? 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.
Given we’re already blocking the majority of spammy emails in Gmail, blocking millions more with precision is a feat. TensorFlow helps us catch the spammers who slip through that less than 0.1 percent, without accidentally blocking messages that are important to users.
Google uses machine learning to block spam with 99.9 percent efficiency
Posted on Thursday, February 07 2019 @ 11:35 CET by Thomas De Maesschalck