Security & Privacy2H Hands-on Lab120min
Shall we play a Game? LLM Security in Practice
This workshop teaches participants how to securely build applications using Large Language Models (LLMs), addressing security risks like data leakage and prompt injection. Through interactive, challenge-based exercises, attendees will gain practical skills and a deeper understanding of LLM security concepts in an engaging, gamified environment.
Joseph KatsioloudesGitHub
Xavier René-CorailGitHub
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.
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.
Joseph Katsioloudes
Joseph is a leading voice in cybersecurity and AI, developing software and content that shape how developers build securely. His open source game gh.io/scg has helped 10K+ developers gain future-proof security skills. His videos, with 2.8M+ views, simplify complex security topics and deliver actionable tips to a global audience. As a speaker, Joseph has delivered 74 talks across 25 countries over the past four years, captivating audiences with his insights and energetic stage presence.
Highlights:
• Creator of gh.io/scg helping 10K+ developers gain security skills
• x3 Guest Lectures at Imperial College’s Advanced Security (3rd Year & MSc)
• 74 talks across 25 countries over the past 4 years
• x2 Sessionize’s Top 3% of most active speakers (2023, 2024)
• 2.8M+ views across 42 videos reaching a global audience
• IBM’s UK & Ireland Top Performer 2020
• Departmental Award for outstanding MSc performance
• Finalist in the 2016 International Student Innovation Awards
Highlights:
• Creator of gh.io/scg helping 10K+ developers gain security skills
• x3 Guest Lectures at Imperial College’s Advanced Security (3rd Year & MSc)
• 74 talks across 25 countries over the past 4 years
• x2 Sessionize’s Top 3% of most active speakers (2023, 2024)
• 2.8M+ views across 42 videos reaching a global audience
• IBM’s UK & Ireland Top Performer 2020
• Departmental Award for outstanding MSc performance
• Finalist in the 2016 International Student Innovation Awards
Xavier René-Corail
Xavier René-Corail est Senior Director du GitHub Security Lab. Sa mission est d'inspirer la communauté open source, les chercheurs en sécurité et les développeurs, à sécuriser les logiciels open source grâce à de meilleures pratiques de sécurité. Avant de rejoindre GitHub, Xavier était responsable Developer Advocacy chez Semmle, acquis par GitHub en 2019, et Engineering Manager chez Murex, où il a piloté le déploiement des pratiques de développement, notamment l'eXtreme Programming (XP), le Test-driven development (TDD), Agile, DevOps, la politique open source.
comments.speakerNotEnabledComments