Using Artificial Intelligence to Catch Sneaky Images in Email

These days, email security is more critical than ever. With the rise of sophisticated cyber threats, attackers are constantly evolving their techniques to bypass traditional security measures. One such method is the use of image-based fraud, which can be particularly challenging to detect and prevent.

The challenge of image-based fraud

Have you ever received an email from a service you don’t remember signing up for? Or perhaps an email that seems legitimate but feels off? Information overload is a common tactic used by attackers to catch their victims off guard. As traditional security controls improve, threat actors pivot their techniques, often aiming to take transactions off the corporate monitored network. This has led to a rise in telephone-oriented attack delivery (TOAD) attacks and other types of image-based fraud.

While this image may be clearly fraudulent to security analysts, it can be very challenging to stop using traditional methods like block rules or regular expressions. In this case, the email itself contained no actual text for traditional anti-spam technologies to spot. Despite the obvious red flags, such as brand abuse, these emails can slip through conventional defenses.

Cisco’s innovative approach to email security

At Cisco, we continue to innovate in the field of email security by leveraging Machine Learning (ML) and Deep Learning (DL) models. These advanced technologies allow us to understand the intention behind messages and identify the true sender. Our approach goes beyond simple analysis to comprehend calls to action within the email content.

Advanced detection techniques

Our data science team utilizes Optical Character Recognition (OCR) detection that leverages Long Short-Term Memory (LSTM) neural networks for content extraction. Email security faces the additional challenge of scale, processing millions of images, URLs, files, QR codes and other objects. New methods of artificial intelligence enable us to use heuristics to determine which images are worth analyzing, processing, and interpreting signals and calls to action. This valuable data enhances our detection engines when assessing intent.

Using data and artificial intelligence to determine attackers’ intent and notice trends in popular evasions allows Cisco Secure Email Threat Defense to stop malicious actors.  You can see these suspicious images and other signals flagged in Email Threat Defense by starting a free trial today.

We’d love to hear what you think. Ask a Question, Comment Below, and Stay Connected with Cisco Security on social!

Cisco Security Social Channels

Instagram
Facebook
Twitter
LinkedIn

Share: