Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Fundamentals of Reverse Engineering ML
"Fundamentals of Reverse Engineering ML" trains professionals to dissect machine learning models and uncover hidden behaviors or vulnerabilities. Use cases include detecting data leakage, embedded bias, and malicious backdoors. Participants learn ethical reverse engineering techniques that contribute to AI security audits and compliance assessments. This course is vital for security researchers and engineers working to validate AI systems against advanced cyber threats.
Course Overview
None
Learning Objectives
- Understand the basic principles of reverse engineering machine learning models.
- Learn techniques for analyzing model behavior and extracting information.
- Identify potential security risks associated with model inversion and extraction attacks.
- Explore methods for defending against reverse engineering of ML models.
- Knowledge of reverse engineering ML is vital for cybersecurity professionals to understand and mitigate threats against AI systems.
Framework Connections
The materials within this course focus on the NICE Framework Task, Knowledge, and Skill statements identified within the indicated NICE Framework component(s):
Competency Areas
Feedback
If you would like to provide feedback on this course, please e-mail the NICCS team at NICCS@mail.cisa.dhs.gov. Please keep in mind that NICCS does not own this course or accept payment for course entry. If you have questions related to the details of this course, such as cost, prerequisites, how to register, etc., please contact the course training provider directly. You can find course training provider contact information by following the link that says “Visit course page for more information...” on this page.