AI security fundamentals
Offered By: Microsoft via Microsoft Learn
Course Description
Overview
- Module 1: Fundamental concepts of AI security
After completing this module, you'll be able to:
- Understand and describe the basic concepts of AI security
- Describe the three layers of AI architecture
- Describe new, AI specific attack techniques
- Module 2: Security controls that you can implement in AI systems to increase the security posture of AI environments
After completing this module, you'll be able to:
- Describe security controls for AI systems
- Understand when these controls should be used
- Understand the types of attacks these controls mitigate
- Module 3: Introduction to AI security testing
After completing this module, you'll be able to:
- Describe AI red teaming
- Understand the three categories of AI red teaming
- Plan an AI red teaming exercise
Syllabus
- Module 1: Module 1: Fundamentals of AI security
- Introduction
- Basic concepts of AI security
- AI architecture layers
- AI jailbreaking
- AI prompt injection
- AI model manipulation
- Data exfiltration
- AI overreliance
- Knowledge check
- Summary
- Module 2: Module 2: AI security controls
- Introduction
- Review AI open-source libraries
- Content filters
- Implement AI data security
- Create metaprompts
- Ground AI systems
- Implement application security best practices for AI enabled applications
- Knowledge check
- Summary
- Module 3: Module 3: Introduction to AI security testing
- What is AI red teaming?
- The three categories of AI red teaming
- Planning AI red teaming
- Knowledge check
- Summary
Tags
Related Courses
Introduction to Artificial IntelligenceStanford University via Udacity Probabilistic Graphical Models 1: Representation
Stanford University via Coursera Artificial Intelligence for Robotics
Stanford University via Udacity Computer Vision: The Fundamentals
University of California, Berkeley via Coursera Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent