How to Detect Business Email Compromise?
Now let’s take a closer look at how we detect fake emails or business email compromised attacks.
These types of phishing attack impersonate executives or suppliers for financial gain. A user receiving one of these two will have a difficult time if it is fake or real. He or she would probably focus on the action they need to take to satisfy the urgent request of an exclusive but what if your users had access to a security expert to help them decide if it was fake. Trend Micro accomplishes this with artificial intelligence that combines the knowledge of a security expert with a self-learning mathematical model to identify fake emails.
Let’s look a little closer; a security expert examining an email would look at both behavioral factors of an email and the intention of the email. In the mail header, the security researcher would look at factors Such as is the email coming from an unsecured email provider? Is the sender’s domain similar to the target organization? Is the sender using a name of an executive at the recipient’s organization and many other factors?
The researcher would also read the content of the email to decipher its intention. Suspicious factors would include a sense of urgency, a request for action or financial implication. We can mimic the decision process of the security researcher with a form of artificial intelligence called an expert system. The rules of the researcher decide which factors of the email to examine and rank whether they are suspicious.
A machine-learning algorithm based on millions of good and fake emails ways the expert rules to more accurately detect fraudulent emails. For additional scrutiny of an email suspected of impersonating an executive at your organization, We examined the style of writing to determine the true author. Our writing style DNA technology first trains a machine learning model of the executives writing style based on previously sent email. We protect privacy during training by capturing metadata to describe the writing style But not the actual text of the email.
When an external email arrives with the same name as the executive, we compare the writing style to the trained model and if they do not match we warn the recipient of a possible impersonation. Using an expert system and machine learning Trend Micro checks your email header, content, and authorship to ensure it’s not from an imposter too damaging business email compromised attacks.
Join GraspHack Family!
We will never spam you.
Be a part of our ever growing community.