Check out and register for the free webinar on February 18, 2025: The use of AI for code generation

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 training 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.

Objective

  • Understand various aspects of responsible AI
  • Essentials of machine learning security
  • How to use generative AI responsibly in software development
  • Prompt engineering for optimal outcomes
  • How to apply generative AI throughout the SDLC

Target audience

All people involved in using GenAI or developing machine learning (developers, testers, managers).

Location (1)
Start date (1)
Duration 1 day (remote)
Frequency Twice per year
Involved
Involved
Price per participant € 800 excl. VAT. *
Keep me posted

Program

A brief history of artificial intelligence

  • The origins of AI
  • Neural networks and “probability engines”
  • Robustness of ML systems
  • Early ML coding tools
  • The AI coding revolution of the 2020s


Responsible AI

  • What is responsible AI?
  • Accountability and transparency
  • Mitigation of harmful bias
  • Validity and reliability
  • Lab – Experimenting with reproducibility in Copilot
  • Explainability and interpretability
  • Safety, security, privacy and resilience
  • Security and responsible AI in software development


An overview of AI and ML security

  • A quick overview of ML for non-specialists
  • GIGO and other well-known ML pitfalls
  • Malicious use of AI
  • Real-life attacks against AI
  • Subverting AI to attack others
  • AI and ML security standards
  • A quick look at ML hacking: evasion
  • A quick look at ML hacking: poisoning
  • A quick look at ML hacking: model inversion
  • A quick look at ML hacking: model stealing
  • The security of large language models


Using GenAI responsibly in software development

  • LLM code generation basics
  • Basic building blocks and concepts
  • GenAI tools in coding: Copilot, Codeium and others
  • Can AI… take care of the ‘boring parts’?
  • Can AI… be more thorough?
  • Can AI… teach you how to code?
  • Lab – Experimenting with an unfamiliar API in Copilot
  • GenAI as a productivity boost
  • The dark side of GenAI
  • Prompt engineering techniques for code generation
  • Integrating generative AI into the SDLC
  • Security of AI-generated code


Summary and takeaways

  • Responsible AI principles in software development
  • Resources and additional guidance

Methods

Live, instructor-led online classroom training. Discussions. Hands-on practice using case studies and live lab exercises.

Certification

Participants will receive a High Tech Institute course certificate for attending this training.