Endpoint

5/31/2017
03:15 PM
Connect Directly
Twitter
LinkedIn
Google+
RSS
E-Mail
50%
50%

Google Arms Gmail Security with Machine Learning

Google rolls out four security updates to protect enterprise Gmail accounts from phishing, data loss, and other threats.

Google is adding four new security measures to protect Gmail business users from spam, phishing, data loss, ransomware, and other workplace security threats.

"Email attacks are constantly evolving, and the email attack vector is by far the preferred way for attackers to gain access to enterprise data," says Gmail product manager Sri Somanchi. "We see all kinds of attacks, including phishing, malware, and ransomware attacks."

Machine learning is a common theme in today's updates. Google reports about 50-70% of the messages Gmail receives are spam, and machine learning helps block it with over 99.9% accuracy. It's aiming to weed out spam with early phishing detection, Google's machine learning model used to selectively delay messages for phishing analysis.

The system learns by comparing genuine messages with a similar pool of fake emails, Somanchi explains. It tracks attributes of each message to find details that differentiate suspicious from legitimate mails, and uses those indicators to perform future phishing checks.

Gmail's phishing detection models integrate with Google Safe Browsing, a machine learning model for detecting phishy URLs. The two models combine techniques, like URL reputation and similarity analysis, to enable URL click-time warnings for malware links. The machine learning systems adapt as they find new patterns with the idea of improving accuracy.

Unintended external reply warnings are intended to help users think twice before sending sensitive data to third parties. If someone tries to respond to someone outside the company domain, they see a warning to verify whether they intended to send that email.

"Using forged emails to target enterprise users to reply with sensitive data has become an increasingly common phishing scam," Somanchi says.

Contextual intelligence determines whether the recipient is an existing or regular contact, so warnings are not displayed unnecessarily. Given the potentially severe consequences of phishing attacks, he continues, the warnings are set by default and can only be disabled by an administrator.

Google notes that it has also implemented defenses against ransomware and polymorphic malware.

"We correlate spam signals with attachment and sender heuristics, to predict messages containing new and unseen malware variants," Somanchi explains. "These protections enable Gmail to better protect our users from zero-day threats, ransomware and polymorphic malware."

All of these features will be available to enterprise users over the next one- to three days. All are also available to consumers, with the exception of unintended external reply warnings.

Today's rollout arrives nearly one month after a Google Doc phishing attack scammed more than one million users. Victims were tricked into clicking a link that enabled access to their Google Drive through OAuth authentication connections, giving the attacker permission to act on behalf of their account.

It also follows Google's February publication of data highlighting security threats putting organizations at risk. Research found attackers send 4.3 times more malware, 6.2 times more phishing emails, and 0.4 times as much spam, to corporate inboxes than to personal email addresses.

Related Content:

Kelly Sheridan is the Staff Editor at Dark Reading, where she focuses on cybersecurity news and analysis. She is a business technology journalist who previously reported for InformationWeek, where she covered Microsoft, and Insurance & Technology, where she covered financial ... View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
JulietteRizkallah
50%
50%
JulietteRizkallah,
User Rank: Ninja
6/6/2017 | 4:04:48 PM
New attack vector is unstructured data
This is welcome news from Google as we will see an increasing amount of breaches through emails which carry many sensitive unstructured data ( think board presentations attached to a gmail account of a Board member).
BPID Security
50%
50%
BPID Security,
User Rank: Strategist
6/1/2017 | 12:38:34 PM
Privacy v. some benefit?
It seems that Google is reading my mail and this is supposed to be a good thing?

If the government read your mail to keep you from getting "junk mail" you would be up in arms. but because it is Google and people do not take the time to learn their tech then it's OK for them to filter based on content.

The fact that Gmail publically states they read your mail, regardless of the benefit (protecting people from their own stupidity) in not a reason to rejoice.

Here is a heuristic tip you can include in your own filtering: "read the fine print". you'll make better decisions than a computer.

 
WebAuthn, FIDO2 Infuse Browsers, Platforms with Strong Authentication
John Fontana, Standards & Identity Analyst, Yubico,  9/19/2018
Turn the NIST Cybersecurity Framework into Reality: 5 Steps
Mukul Kumar & Anupam Sahai, CISO & VP of Cyber Practice and VP Product Management, Cavirin Systems,  9/20/2018
NSS Labs Files Antitrust Suit Against Symantec, CrowdStrike, ESET, AMTSO
Kelly Jackson Higgins, Executive Editor at Dark Reading,  9/19/2018
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Current Issue
Flash Poll
The Risk Management Struggle
The Risk Management Struggle
The majority of organizations are struggling to implement a risk-based approach to security even though risk reduction has become the primary metric for measuring the effectiveness of enterprise security strategies. Read the report and get more details today!
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2018-17538
PUBLISHED: 2018-09-26
Axon (formerly TASER International) Evidence Sync 3.15.89 is vulnerable to process injection.
CVE-2018-11763
PUBLISHED: 2018-09-25
In Apache HTTP Server 2.4.17 to 2.4.34, by sending continuous, large SETTINGS frames a client can occupy a connection, server thread and CPU time without any connection timeout coming to effect. This affects only HTTP/2 connections. A possible mitigation is to not enable the h2 protocol.
CVE-2018-14634
PUBLISHED: 2018-09-25
An integer overflow flaw was found in the Linux kernel's create_elf_tables() function. An unprivileged local user with access to SUID (or otherwise privileged) binary could use this flaw to escalate their privileges on the system. Kernel versions 2.6.x, 3.10.x and 4.14.x are believed to be vulnerabl...
CVE-2018-1664
PUBLISHED: 2018-09-25
IBM DataPower Gateway 7.1.0.0 - 7.1.0.23, 7.2.0.0 - 7.2.0.21, 7.5.0.0 - 7.5.0.16, 7.5.1.0 - 7.5.1.15, 7.5.2.0 - 7.5.2.15, and 7.6.0.0 - 7.6.0.8 as well as IBM DataPower Gateway CD 7.7.0.0 - 7.7.1.2 echoing of AMP management interface authorization headers exposes login credentials in browser cache. ...
CVE-2018-1669
PUBLISHED: 2018-09-25
IBM DataPower Gateway 7.1.0.0 - 7.1.0.23, 7.2.0.0 - 7.2.0.21, 7.5.0.0 - 7.5.0.16, 7.5.1.0 - 7.5.1.15, 7.5.2.0 - 7.5.2.15, and 7.6.0.0 - 7.6.0.8 as well as IBM DataPower Gateway CD 7.7.0.0 - 7.7.1.2 are vulnerable to a XML External Entity Injection (XXE) attack when processing XML data. A remote atta...