NGC | Catalog
CatalogCollectionsDigital Fingerprinting to Detect Anomalies

Digital Fingerprinting to Detect Anomalies

For contents of this collection and more information, please view on a desktop device.
Logo for Digital Fingerprinting to Detect Anomalies

Description

Analyze the behavior of every human and machine across the network to detect and react to anomalies on a scale previously impossible.

Curator

NVIDIA

Modified

May 23, 2023
Containers
Helm Charts
Models
Resources

Overview

NVIDIA Digital Fingerprinting AI workflow implements unsupervised learning to uniquely fingerprint every user, service, account, and machine across a network and provide intelligent alerts with actionable information enabling cybersecurity analysts to act on threats faster.

Digital fingerprinting includes example training and inferencing pipelines built using the NVIDIA Morpheus cybersecurity AI framework, pretrained models, Jupyter Notebooks, Helm Charts, and documentation to help organizations get started more quickly in building a cybersecurity threat detection AI solution.

image1

Key benefits of the digital fingerprinting AI solution workflow:

  • Applies GPU accelerated AI to provide 100 percent data visibility and uniquely fingerprints every user, service, account, and machine.

  • Includes intelligent alerts with actionable information.

  • Enables cybersecurity analysts to identify, capture, and act on threats faster with visualization.

  • Reduces hundreds of millions of events per week to 8-10 potentially actionable insights daily.

  • Cuts the time to detect from weeks to minutes, for certain attack patterns.

Getting Started

To get started, review the documentation linked below for more information on what is included in the workflow, and how to deploy and run the workflow.

Documentation

Additional Resources

Learn more about how to use NVIDIA Morpheus through our Deep Learning Institute platform. Access the course here.

License

By pulling and using the containers or Helm Charts, you accept the terms and conditions of this End User License Agreement.