Résumé du cours
Traditional cybersecurity methods include creating barriers around your infrastructure to protect it from intruders. However, as enterprises continue to digitally transform, they’re faced with a proliferation of devices, more sophisticated cybersecurity attacks, and an incredibly vast network of data to protect—which means new cybersecurity methodologies must be explored. An alternative approach is to address cybersecurity as a data science problem: Aim to better understand all the users and activities across your network so that you can identify which transactions are typical and which are potentially nefarious.
Please note that once a booking has been confirmed, it is non-refundable. This means that after you have confirmed your seat for an event, it cannot be cancelled and no refund will be issued, regardless of attendance.
Moyens d'évaluation :
- Quiz pré-formation de vérification des connaissances (si applicable)
- Évaluations formatives pendant la formation, à travers les travaux pratiques réalisés sur les labs à l’issue de chaque module, QCM, mises en situation…
- Complétion par chaque participant d’un questionnaire et/ou questionnaire de positionnement en amont et à l’issue de la formation pour validation de l’acquisition des compétences
Pré-requis
- Familiarity with defensive cybersecurity themes
- Professional data science and/or data analysis experience
- Competency with the Python programming language
- Competency with the Linux command line
Objectifs
- Build Morpheus pipelines to process and perform AI-based inference on massive amounts of data for cybersecurity use cases in real time
- Utilize several AI models with a variety of data input types for tasks like sensitive information detection, anomalous behavior profiling, and digital fingerprinting
- Leverage key components of the Morpheus AI framework, including the Morpheus SDK and command-line interface (CLI), and NVIDIA Triton™ Inference Server
Contenu
Introduction
- Meet the instructor.
- Create an account at courses.nvidia.com/join
An Overview of the NVIDIA Morpheus AI Framework
- Explore the fundamental mechanics and tools involved in successfully training deep neural networks:
- Understand the need for AI-based cybersecurity.
- Learn about the components of the Morpheus framework.
- Discover how institutions are building solutions with Morpheus.
Morpheus Pipeline Construction
- Get an overview of the Morpheus SDK and CLI.
- Learn about pipeline types and commands.
- Learn about data input/output (IO) and processing.
Inference in Morpheus Pipelines
- Get an overview of NVIDIA Triton Inference Server.
- Understand how models are deployed.
- Explore a sensitive-information-detection pipeline.
Case Study: AI-Based Machine Logs Parsing at Splunk
- Apply your understanding to a real-world example.
Digital Fingerprinting Pipeline
- Use the Morpheus autoencoder pipeline.
- Discover compromised credentials.
Time Series Analysis
- Apply time series analysis within a Morpheus pipeline.
- Combine time series analysis with digital fingerprinting.
Case Study: Cybersecurity Flyaway Kit at Booz Allen Hamilton
- Apply your understanding to a real-world example.
Assessment 1: Test Your Understanding
- Assess your conceptual understanding of the topics covered.
Assessment 2: Practical Demonstration
- Build an end-to-end Morpheus pipeline to identify a cybersecurity breach.
Wrap Up
- Get resources for further development with Morpheus.
- Provide feedback on the workshop.
Moyens Pédagogiques :