Google is adding new security features for Gmail customers, including early phishing detection using machine learning, click-time warnings for malicious links, unintended external reply warnings and built-in defenses against new threats.

Machine learning helps Gmail block sneaky spam and phishing messages from showing up in your inbox with over 99.9 percent accuracy, according to Google. Google is continuing to improve spam detection accuracy with early phishing detection, a dedicated machine learning model that selectively delays messages (less than 0.05 percent of messages on average) to perform phishing analysis and further protect user data from compromise.

The detection models integrate with Google Safe Browsing machine learning technologies for finding and flagging phishy and suspicious URLs. These new models combine a variety of techniques such as reputation and similarity analysis on URLs, allowing Google to generate new URL click-time warnings for phishing and malware links. As new patterns are found, Google's models adapt more quickly than manual systems ever could, and get better with time.

In addition, Gmail now displays unintended external reply warnings to users to help prevent data loss. Now, if you try to respond to someone outside of your company domain, you'll receive a quick warning to make sure you intended to send that email.

With new built-in defenses against ransomware and polymorphic malware, Gmail now blocks millions of additional emails that can harm users. Google classifies new threats by combining thousands of spam, malware and ransomware signals with attachment heuristics (emails that could be threats based on signals) and sender signatures (already marked malware).