Platform
Generative AI
Audience
All people involved in using GenAI or developing machine learning
Preparedness
General development
Standards and references
NIST
Group size
12 participants
Outline
What you will learn
Description
Generative AI is inevitably transforming the software industry. Tools like ChatGPT or GitHub Copilot enable developers to code more efficiently than ever before. While this sparks excitement, it also raises concerns, and so many stakeholders tend to balance this optimism with caution. Though these tools are advancing rapidly, to date they still lack the necessary sophistication to consider various subtle but important aspects of software products. This course emphasizes the importance of understanding this evolution through the well-established principles of Responsible AI.
After a short overview of AI and specifically responsible AI, participants delve into the complex world of machine learning (ML), focusing on how these solutions can be compromised. Threats and vulnerabilities such as model evasion, poisoning, and inversion attacks are explained in a simple way, via real-world case studies and live demonstrations. Finally, we overview the security challenges of large language models (LLMs), exploring the practical defenses as well.
The course then highlights the capabilities and limitations of generative AI (GenAI) tools – like GitHub Copilot, Codeium or others -, offering insights into their role in code generation and beyond. Topics include smart prompt engineering, not only during the implementation phase, but also during requirements capturing, design, testing, and maintenance. Participants will learn best practices and pitfalls of using AI-generated code, with hands-on labs demonstrating potential security flaws such as dependency hallucination and path traversal. By the end, software engineers and managers will have a clear understanding of how to responsibly integrate GenAI tools into the various stages of the software development lifecycle.
A must-have primer to those concerned about using GenAI tools in their software development projects. Building on these foundations, and depending on the technology stack, we suggest continuing with one of the Generative AI courses - see Code responsibly with generative AI in C++/Java/C#/Python. However, if you develop machine learning solutions, you can also continue your journey with the comprehensive 4-day Machine learning security course.