Speakers

Artificial Intelligence (AI) is no longer a futuristic concept. It's embedded in the systems we use daily. At the core of these innovations are Large Language Models (LLMs). These LLMs can unlock new capabilities but can also introduce novel security challenges due to their non-deterministic behavior and autonomous outputs, causing issues like data leakage and unintended model behavior from attacks such as prompt injection. This workshop equips participants with the skills they need to build secure LLM-based applications through interactive, challenge-based exercises that gamify core security concepts. Prepare to level up your understanding of LLM security in a practical and fun way.Key Learnings:1. Gain insight into real-world LLM issues, such as prompt injection and internal data leakage, and understand why traditional measures fall short.2. Learn how to apply secure development practices—like I/O validation, robust system messages, LLM self-verification, and effective data access control—to mitigate risks unique to LLMs.3. Discover how gamified challenges can reinforce security concepts and improve your ability to identify and fix AI-specific vulnerabilities in development.Prerequisites:Attendees must have a GitHub account to get started with the workshop for free in under two minutes. This removes the need for any local installations, as the entire workshop can be run directly in a web browser using GitHub Codespaces—an online code editor that automatically installs all required dependencies via our setup scripts. Read More...