Google has announced new security features for Gmail customers, which include early phishing detection using machine learning and click-time warnings for malicious links. In addition, Google has updated defenses against malicious attachments. Google will correlate spam signals with attachment and sender heuristics to predict messages containing new and unseen malware variants. These protections enable Gmail to better protect us from zero-day threats, ransomware and polymorphic malware. Along with all these protections, Google blocks use of file types that carry a high potential for security risks including executable and javascript files.
Machine learning has helped Gmail achieve more than 99% accuracy in spam detection, and with these new protections, Google is able to reduce your exposure to threats by confidently rejecting hundreds of millions of additional messages every day.
These new changes are just the latest in Google’s ongoing work to improve protections to keep ahead of evolving threats. For many years, scammers have tried to use dodgy email attachments to sneak past Google spam filters, and Google has long blocked this potential abuse in a variety of ways, including:
- Rejecting the message and notifying the sender if Google detects a virus in an email.
- Preventing you from sending a message with an infected attachment.
- Preventing you from downloading attachments if Google detects a virus.
