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:
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.
- Cybersecurity Forecast 2022: Snowpocalypse or cloudy with a chance of rain?
- Preventing Attackers from Navigating Your Enterprise Systems
- Protecting Enterprise Data from Malicious Insiders
- Beyond Patch Management: Next-Generation Approaches to Finding and Fixing Vulnerable Code
- Getting SASE: What Every Enterprise Should Know