Phishing: how it stops with mechanical learning

Phishing vs AI: When the Cloud company Twilio acquired SendGrid for $ 2 billion, many wondered what the move was about.

Of course it was not just about sending emails from the SendGrid platform. Immediately after its acquisition, Twilio became one of the largest companies in the corporate battle against phishing.

Phishing

Cyber-fishing has been around since the early days of email, and due to its increasing complexity, the method is still a major threat to business networks.

According to some estimates, phishing attacks cost businesses an average of $ 1,6 million per attack.

The Twilio SendGrid approach uses AI to stop phishing emails before they reach the end user's inbox.

With Twilio's SendGrid platform you can send email confirmations , password reset instructions or messages about an upcoming sale. Developers and marketers use SendGrid to build, segment, test, and deliver emails.

The company, for its part, says it processes more than 50 billion emails every month, and because of that scale, it was able to train a system of learning called Fisherman. The system can "catch" phish before they reach the customer.

TensorFlow is the book machine learning and open source, which has become one of the most popular platforms for building machine learning and deep learning applications.

With Phisherman, the Twilio SendGrid platform uses a trained neural network to determine when an email can be considered phish. The system uses comparisons to identify patterns in large sets from a huge variety of mail, which are then compared to a model designed to isolate phish messages from regular electronic mail.

Thanks to Phisherman, the company states that its platform offers 99,7% security.

_________________

iGuRu.gr The Best Technology Site in Greecefgns

every publication, directly to your inbox

Join the 2.081 registrants.

Written by giorgos

George still wonders what he's doing here ...

Leave a reply

Your email address is not published. Required fields are mentioned with *

Your message will not be published if:
1. Contains insulting, defamatory, racist, offensive or inappropriate comments.
2. Causes harm to minors.
3. It interferes with the privacy and individual and social rights of other users.
4. Advertises products or services or websites.
5. Contains personal information (address, phone, etc.).