> Markdown version of [/events/world-congress-2026-europe/sessions/1146-shall-we-play-a-game](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1146-shall-we-play-a-game). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Shall we play a Game? LLM Security in Practice


- **Date:** Thursday, Jul 9, 2026
- **Time:** 15:30–17:30 (120 min)
- **Room:** Room R2 (30 Seats)
- **Event:** World Congress 2026 Europe

## Description

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.

## Speaker

### [Joseph Katsioloudes](https://www.wearedevelopers.com/@joseph-katsioloudes)

Senior Developer Advocate at GitHub


## Related talks at this congress

- [From Hallucination to Justification: Hands-On Explainability for LLMs](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1239-from-hallucination) — Lucía Conde-Moreno, Tessel Haagen
- [Dangerous Reactivity: Why AI Output Is the New XSS](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1116-dangerous-reactivity) — Ramona Schwering
- [The LLM Evolution: From Sequence Imitation to Verifiable Reasoning](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1377-the-llm-evolution) — Kamen Petroff
- [Fine-Tuning Small Language Models for Agentic AI](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1389-fine-tuning-small) — Björn Buchhold