Google’s services, which are ubiquitous on the Internet, have clearly become the preferred target for many ulterior motives. The company has been trying to apply the latest technology to combat illegal activity targeting Gmail users, including spam, phishing scams, malware attacks, and more. The latest news is that Google is using deep learning to scan and block malicious attachments in messages.
Whether it’s using a free or paid version of the service, Google wants to further increase customer satisfaction.
Previously, the company had implemented spam filtering for the body of the message, and could even help users categorize by specific topics. Even so, the industry has been lacking an effective response to email attachments, and its potential harm is even more significant.
Google is proud to say that it is now able to handle 300 billion attachments a week. However, the strategies used by cybercriminals are also developing, and static systems often fail to keep up in a timely manner.
The good news is that artificial intelligence (AI) and machine learning can be analyzed and learned faster than humans. In the case of large amounts of data involved, the advantages are even more obvious.
At the end of 2019, the company deployed a new deep learning document scanner, reporting a significant (but not surprising) improvement of about 10 percent. However, in the event of a sudden attack, it is said to increase power by 150%.
It’s important to note that the new attachment scanner is still in its infancy and focuses only on the document level (58 percent of Gmail’s malicious attachments), so there’s plenty of room for growth in the future. As for how to protect the privacy of users, another matter.