Siamese 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.
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
Why Effective Asset Management is Critical to Enterprise Cybersecurity
May 21, 2024Finding Your Way on the Path to Zero Trust
May 22, 2024Extending Access Management: Securing Access for all Identities, Devices, and Applications
June 4, 2024Assessing Software Supply Chain Risk
June 6, 2024Preventing Attackers From Wandering Through Your Enterprise Infrastructure
June 19, 2024
Black Hat USA - August 3-8 - Learn More
August 3, 2024Cybersecurity's Hottest New Technologies: What You Need To Know
March 21, 2024