Google says that malicious documents currently represent 58% of all malware that targets Gmail users, and that it is fighting back by employing "Deep Learning" AI to prevent this malware from reaching your inbox.

One of Google's key protections is a malware scanner that processes more than 300 billion attachments each week to block harmful content. Google says that 63% percent of the malicious documents blocked differ from day to day. To stay ahead of this constantly evolving threat, Google recently added a new generation of document scanners that rely on deep learning to improve our detection capabilities.

Since the new scanner launched at the end of 2019, Google says it has increased the daily detection coverage of Office documents that contain malicious scripts by 10%.

"Our technology is especially helpful at detecting adversarial, bursty attacks. In these cases, our new scanner has improved our detection rate by 150%," said Google's Gmail Security unit.

Under the hood, Google's new scanner uses a distinct TensorFlow deep-learning model trained with TFX (TensorFlow Extended) and a custom document analyzer for each file type. The document analyzers are responsible for parsing the document, identifying common attack patterns, extracting macros, deobfuscating content, and performing feature extraction.

Strengthening the document detection capabilities is one of Google's key focus areas, as malicious documents represent 58% of the malware targeting Gmail users. Google is still actively developing this technology, and right now, the company only uses it to scan Office documents.