AI Security and Red Teaming
Covers prompt injection, jailbreaking, guardrails, moderation, red teaming, and GDPR compliance for AI.
14 lessons About 1 h 45 min Advanced
What you'll learn
- Map risks specific to applications based on language models
- Identify and prevent prompt injection attacks and jailbreak attempts
- Implement input and output validation guardrails
- Leverage moderation APIs and multi-layer filtering
- Conduct a red teaming exercise and document findings
Course details
- Who it's for
- Developers, engineers, and integrators looking to leverage ChatGPT via API in their applications.
- Prerequisites
- Proven experience in application development and deployment.
- Length
- 1 h 45 min · 14 lessons
- Format
- 100% online self-paced course, accessible 24/7 from a browser. Progress is saved, allowing you to resume at any time. Estimated duration: 1 h 45 min.
- Assessment
- Application exercises provided throughout the lessons. Each lesson ends with its Key takeaways, supporting self-assessment. A final quiz of 5 corrected questions, at the end of the last lesson, validates acquired skills.
- Accessibility
- Self-paced course accessible to people with disabilities: text content compatible with screen readers, keyboard navigation, and compliant contrasts. For any adaptation needs, email [email protected].
- Price
- Free
- Recognition
- Certificate of completion issued by Corsen AI, verifiable online.
- Syllabus
- Download the syllabus (PDF)