SecAppDev 2025 Faculty
Laurens Sion
Research Expert, DistriNet, KU Leuven
Laurens Sion is a Research Expert on Privacy Engineering at the DistriNet research group at the Department of Computer Science at KU Leuven. His research focuses security and privacy threat modeling and automating several facets of threat modeling (creating models, elicitation, risk analysis, etc.). His research interests are in how these design-level analysis activities for security and privacy activities integrate in other development activities (DevOps), such as the automated reconstruction of design models (or verifying their correspondence with code) to enable a tighter integration as part of continuous integration pipelines.
LLM Security Bootcamp: Foundations, Threats, and Defensive Techniques
One-day workshop by Thomas Vissers and Tim Van Hamme and Laurens Sion in room Lemaire
Thursday June 5th, 09:00 - 17:30
Large Language Models (LLMs) open up a new realm of possibilities in application development, but they also pose significant challenges. Their non-deterministic nature and broad use cases complicate testing, while unpredictable failures (“hallucinations”) and novel attack vectors (“prompt injections”) add risk.
This workshop covers LLM-based applications, highlights unique threats, and offers hands-on testing and hardening techniques. Attendees will learn to set up and secure basic LLM-driven solutions in their organizations.
Learning goal: Learn how LLM applications work and are architected, the unique security challenges they introduce, and the current best practices in LLM security—along with their limitations.