Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
- Learn about AI security fundamentals including how AI security differs from traditional cybersecurity, the three-layer AI architecture model, and AI-specific attack techniques like jailbreaking, prompt injection, and data exfiltration.
After completing this module, you'll be able to:
- Describe how AI security differs from traditional cybersecurity
- Identify the three layers of AI architecture and the security concerns at each layer
- Explain AI-specific attack techniques, including jailbreaking, prompt injection, model manipulation, data exfiltration, and overreliance
- Describe mitigation strategies for each attack type
- Learn about the security controls you can implement to protect AI systems, including content filters, metaprompts, data security, grounding, and monitoring.
After completing this module, you're able to:
- Evaluate open-source AI libraries for security risks
- Describe content filtering and data security controls for AI systems
- Design metaprompts and grounding strategies as security controls
- Apply application security best practices to AI-enabled applications
- Describe monitoring strategies for detecting AI-specific threats
- Learn about AI red teaming, the three categories of AI security testing, and how to plan and execute red teaming exercises for LLMs and AI-enabled applications.
After completing this module, you're able to:
- Describe what AI red teaming is and how it differs from traditional security testing
- Identify the three categories of AI red teaming and the skills each requires
- Plan an AI red teaming exercise, including team composition and testing methodology
- Describe how automated red teaming tools complement manual testing
