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.


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 the Twilio SendGrid platform, you can send emails for purchase confirmations, password reset instructions, or messages for 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 each month, and because of this scale, has been able to train a TensorFlow machine learning system called Phisherman. The system can "catch" phish before they reach the customer.

TensorFlow is the open source library of machine learning, which has become one of the most popular platforms for creating learning machines 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 detect patterns in large datasets from a huge variety of mail, which are then compared to a model designed to isolate phish messages from regular emails.

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




Subscribe to the Blog via Email

Enter your email to subscribe to the email notification service for new posts.

Read them Technology News from all over the world, with the validity of

Follow us on Google News at Google news