Siamese Neural Networks for Detecting Brand ImpersonationSiamese Neural Networks for Detecting Brand Impersonation
Brand impersonation is a common attack strategy in which attackers craft content to look like a known brand to deceive victims. A team of Microsoft researchers developed and trained a Siamese Neural Network, based on a dataset of more than 50,000 screenshots of known malicious log-in pages encompassing more than 1,000 impersonations, to better detect these attacks. Here, a member of the team discusses their work.
August 12, 2021

The Dark Reading News Desk interviews Justin Grana, applied researcher at Microsoft, about his team's work to develop and train a Siamese Neural Network:
Read more about:
Black Hat NewsAbout the Author(s)
You May Also Like
Hacking Your Digital Identity: How Cybercriminals Can and Will Get Around Your Authentication Methods
Oct 26, 2023Modern Supply Chain Security: Integrated, Interconnected, and Context-Driven
Nov 06, 2023How to Combat the Latest Cloud Security Threats
Nov 06, 2023Reducing Cyber Risk in Enterprise Email Systems: It's Not Just Spam and Phishing
Nov 01, 2023SecOps & DevSecOps in the Cloud
Nov 06, 2023