AI: Responsible AI
AI security: prompt injection & red-teaming | Sri AI
Advanced
2 views
Course overview
How AI systems get attacked through their inputs, documents and tools, and how to test and defend your own.
Level: Advanced · Mode: Evenings, online
Who this course is for
Security engineers and developers shipping AI.
What you will learn
- Explain prompt injection and data leakage
- Scan models and apps for weaknesses
- Red-team an agent
- Design defences in layers
Syllabus
- Module 1: The AI attack surface
- Module 2: Prompt injection
- Module 3: Tool and data abuse
- Module 4: Automated scanning
- Module 5: Defence in depth
Final project
Every module ends in hands-on practice, and the course ends with a project you build and present. Your certificate names that project.
Before you start
Agentic AI fundamentals.