Gurucul's behavior based security analytics is powered by robust machine learning models built by data scientists.
Our competitors use signatures, patterns, rules and policies which can only detect known behavior patterns. What about the unknowns? Our models go beyond detecting known or common patterns so you can detect unknown threats.
Below are the models we revealed at Black Hat. These are actual Machine Learning Models we use to detect and stop insider threats, data exfiltration, privileged access abuse, cyber fraud and more. These are just a few of our library of over 1000 Machine Learning Models.
Please check our blog regularly over the next few months for in depth details on how each of these models work:
- Email Fuzzy Logic: Detect and stop insider threats
- Predictive Flight Risk: Monitor departing users
- Entitlement Classification: Discover all of your privileged accounts and entitlements
- Linear Regression: Prevent privileged access abuse
- Domains Generated Algorithmically: Prevent host or entity compromise
- Workflow with Classification Regression Tree: Dynamically provision access based on risk score
- Clustering and K-Means: Identify outlier access
- Abnormal PowerShell Command Execution: Detect fileless malware
- Rare and Volume Based Analytics: Detect and prevent fraud
- Dimensionality Reduction: Anti-money laundering made easy!
- Feature Analysis: It's all in the data - "Garbage in Garbage Out"
- Link Analysis: Streamline your investigations
- Identity Classification: Dynamically adjust controls without human intervention
- Outlier Categorical Model: Detect merchant fraud
Request a Personalized Demo