course
Secure AI Programming
Learn to build secure AI applications and recognize and mitigate the most critical security risks in Large Language Model systems.
Description
AI applications introduce new security risks that don't appear in traditional security frameworks. This course centers on the OWASP Top 10 for Large Language Models: a practical guide to the most critical vulnerabilities in LLM-based systems.
You'll not only learn to recognize the risks but also how to defend against them effectively — whether you're building, integrating, or auditing an AI application. The focus is on practical application: from prompt injection to excessive agency, you understand how attacks work and how to prevent them.
This course is designed for developers, architects, DevOps engineers, testers and product owners who:
- integrate AI functionality into their applications
- want to understand the new security risks that come with it
- want to take concrete steps to secure their AI systems
Learning Goals
 Identify the OWASP Top 10 risks specific to LLM-based applications | Remember  |
| Defend against prompt injection attacks and describe mitigation strategies | Understand  |
| Explain how improper output handling can lead to downstream exploits | Understand |
| Apply input and output validation techniques for LLM integrations | Apply  |
| Implement access control and least privilege in LLM-based systems | Apply |
| Apply appropriate safeguards to mitigate risks in agentic AI systems | Apply |
Prior Knowledge
- Basic knowledge of software development
- Familiarity with using LLM APIs (e.g. OpenAI, Azure OpenAI) is a plus
Subjects
- Introduction to AI security and the OWASP LLM Top 10
- LLM01: Prompt Injection
- LLM02: Sensitive Information Disclosure
- LLM03: Supply Chain Vulnerabilities
- LLM04: Data and Model Poisoning
- LLM05: Improper Output Handling
- LLM06: Excessive Agency
- LLM07: System Prompt Leakage
- LLM08: Vector and Embedding Weaknesses
- LLM09: Misinformation
- LLM10: Unbounded Consumption
- Security patterns for AI applications in practice
Schedule
All courses can also be conducted within your organization as customized or incompany training.
Our training advisors are happy to help you provide personal advice or find Incompany training within your organization.
"Very pleasant teacher, gave a very good interpretation of the course in their own way. It was nice to follow the course like that."Marieke
-
Hoge waardering
-
Praktijkgerichte trainingen
-
Gecertificeerde trainers
-
Eigen docenten