Connect with us

Hi, what are you looking for?

SecurityWeekSecurityWeek

Email Security

Google Uses Artificial Neural Network to Detect Sneaky Spam

Google has shared some details on the systems it has implemented to protect its customers against spam emails. The search giant has also released a new tool to help organizations ensure that their emails don’t end up in the spam folder.

Google has shared some details on the systems it has implemented to protect its customers against spam emails. The search giant has also released a new tool to help organizations ensure that their emails don’t end up in the spam folder.

According to Google, the anti-spam features introduced over the past period have led to only less than 0.1 percent of emails in a Gmail inbox being spam. Furthermore, the company says less than 0.05 percent of wanted emails are sent to the spam folder.

In an effort to help companies ensure that the emails they send to their customers don’t end up in the spam folder, Google has launched Gmail Postmaster Tools. The new tool is designed to help companies that send out a high volume of emails conduct an analysis of their messages. Users are provided spam reports, reputation analysis, and data on email delivery errors to help them diagnose potential issues and follow best practices.

While Postmaster Tools is a service for organizations, Google believes it is also beneficial for regular users since they will no longer have to search their spam folder for potentially important information such as bank statements and airline ticket receipts.

In addition to the introduction of Postmaster Tools, Google has revealed a series of steps it has taken to fight spam. The search giant has pointed out that every time users mark an email as spam or not spam, they actually train Gmail’s filters to better distinguish wanted from unwanted emails.

Google says it has applied the intelligence used in Google Search and Google Now to the spam filter.

One of the new spam-fighting techniques involves the use of an artificial neural network for detecting and blocking “especially sneaky” spam.

The spam filter has also been improved to detect email impersonation, which is often used in phishing attacks.

Advertisement. Scroll to continue reading.

“Thanks to new machine learning signals, Gmail can now figure out whether a message actually came from its sender, and keep bogus email at bay,” explained Sri Harsha Somanchi, a Google product manager.

Machine learning has also been used to teach the spam filter to operate based on the individual preferences of each user. This is important, Google has highlighted, because some users like emails such as newsletters and others don’t.

Related: Facebook Reveals New Security Tool

Related: Google Releases Chrome Extension to Protect Users Against Phishing Attacks

Written By

Eduard Kovacs (@EduardKovacs) is a managing editor at SecurityWeek. He worked as a high school IT teacher for two years before starting a career in journalism as Softpedia’s security news reporter. Eduard holds a bachelor’s degree in industrial informatics and a master’s degree in computer techniques applied in electrical engineering.

Click to comment

Trending

Daily Briefing Newsletter

Subscribe to the SecurityWeek Email Briefing to stay informed on the latest threats, trends, and technology, along with insightful columns from industry experts.

Join the session as we discuss the challenges and best practices for cybersecurity leaders managing cloud identities.

Register

The AI Risk Summit brings together security and risk management executives, AI researchers, policy makers, software developers and influential business and government stakeholders.

Register

People on the Move

Retired U.S. Army General and former NSA Director Paul M. Nakasone has joined the Board of Directors at OpenAI.

Jill Passalacqua has been appointed Chief Legal Officer at autonomous security solutions provider Horizon3.ai.

Cisco has appointed Sean Duca as CISO and Practice Leader for the APJC region.

More People On The Move

Expert Insights