Program Schedule

Hacking AI Guardrails Workshop (LISA) by Thomas Vissers and Tim Van Hamme

09:00 - 12:30

Abstract:

In this workshop, participants will get hands-on experience both building and breaking AI guardrails. Working in teams, you’ll design guardrail policies to defend sensitive data within a vulnerable AI application, while attempting to bypass those of others. Who will win? The scoreboard will tell, but in the end everyone walks away with a deeper grasp of how LLMs can be manipulated and the challenges of building robust guardrails.
This workshop is delivered as part of the VLAIO research project LISA.

Bio:

Thomas Vissers specializes in the dynamic intersection of cybersecurity and AI. He packs 10 years of experience in developing and operating production-grade AI security systems. Previously at Cloudflare, he served as an engineering leader for data-driven security products, scaling innovations to protect millions of internet users worldwide. Today at KU Leuven, Thomas focuses on empowering organizations to securely and reliably leverage LLM technology.

Tim Van hamme is a computer scientist specialized in AI security and behavioral analysis, leading research at KU Leuven's DistriNet on secure and trustworthy AI adoption. As co-lead of Blue41, he bridges rigorous academic research with industry applications, helping organizations safely deploy AI systems. With experience spanning from CERT.be's threat intelligence infrastructure to behavioral biometrics and AI agent security, Tim combines theoretical expertise with practical solutions for emergent AI security challenges.

Requirements:

Requirements: laptop that can SSH into external machine.
Optional: running Python locally and an IDE.

Keep your systems secure - a guide to vulnerability management by Olle E. Johansson

09:00 - 17:00

Abstract:

The EU Cyber regulations and common sense all point to one thing: Keep your systems up to date. Manufacturers and users needs to be ready to detect, react and mitigate quickly. We don't know when, but there will be a next "Log4J" issue and this time we need to be better prepared. This sounds easy, but involves a lot of systems from asset management to SBOM inventory, vulnerability intelligence and update awareness and readiness.
In this training we will cover the current state of vulnerability management, go through Software Bill of Materials, regulation requirements and an overview of the existing systems - CVE, NVD, EUVD and classifications like CVSS, EPSS and CWE. What works and what doesn't work? And what kind of tools are available as Open Source?

Bio:

Olle E. Johansson has over twenty years of experience in telecommunications, VoIP, and cybersecurity. Olle is active in open-source projects and standard forums, the founder of major appsec and network security initiatives, and a specialist for various categories of software bills of materials (SBOM). These days, SBOMs are everywhere, but not every SBOM use is equally successful. Olle will tell us how to improve their application, how to work with them day in and day out and how to develop your own SBOM lifestyle for your organization.

Threat modeling with AI by Steven Wierckx

09:00 - 17:00

Abstract:

This workshop aims to introduce Security Professionals, Developers, Architects, and Product Managers to integrating AI assistance into their threat modeling workflows. In this session, participants will learn how to leverage AI for diagramming, threat identification, and countermeasure recommendations to speed up threat model analysis.
To bring these concepts to life, the workshop includes a guided case study on a Digital Wallet / Payment App, where participants will use AI tools to generate a data flow diagram, identify threats using STRIDE, propose mitigations mapped to industry standards, and summarize findings for business stakeholders. This integrated exercise provides an engaging, end-to-end view of how AI can support—but not replace—human judgment in threat modeling.

Bio:

I’m a secure development life-cycle security (SDLC) specialist with more than 20 years of experience in creating and teaching courses, programming, security testing, source code review, test automation, functional and technical analysis, development, and database design. I have guided organizations in achieving compliance for their SDLC for FDA MDR and ISO 27001. I am a team player with a constant drive to learn new things. I have a passion for all aspects of the secure development lifecycle, I have guided many customers in their efforts to reach a secure development practice. I have spoken or thought courses at conferences such as OWASP AppSec USA, O’Reilly Security Conference, Hack In The Box Amsterdam, 44CON, BlackHat EU and BruCON. I have created (and thought) several courses on threat modelling, secure programming, security awareness and testing software for security.

Requirements:

While participants should have a working knowledge of Generative AI and LLM concepts and tools (e.g., prompt engineering), no prior experience with threat modeling is required.

Bring a laptop, have at least access to one AI chatbot of your choice, no other tools required. Both free and paying versions of AI chatbots can be used.

Preparing for the EU Cyber Resilience Act with OWASP SAMM by Nariman Aga-Tagiyev

09:00 - 17:00

Abstract:

This full-day, interactive workshop provides a detailed understanding of the EU Cyber Resilience Act (CRA) and its implications for organizations producing products with digital and software components. We will deep dive into how OWASP SAMM (Software Assurance Maturity Model) can help your organization get ready for it. We will explore the CRA’s key requirements - including its timeline, affected product categories, impact on Open Source Software, financial penalties, and expected application security activities. You’ll gain a clear understanding of how SAMM maps to CRA obligations and how it can serve as a practical foundation for compliance and continuous improvement.

Through interactive exercises and group discussions, participants will learn how to perform SAMM assessments, address organizational and cultural challenges, and prioritize improvements based on company context. We’ll dive deep into SAMM’s activities, discuss success criteria's, and connect it with related frameworks such as DSOMM and AI Maturity. By the end of the day, you’ll walk away with a clear set of next steps to elevate your application security maturity and prepare effectively for the EU CRA.

Bio:

Nariman Aga-Tagiyev is an Application Security Architect with over two decades of experience in software development. Throughout his career, Nariman has worn many hats, serving as a developer, software architect, DevSecOps engineer, and cloud architect.

Since 2016, however, he has focused exclusively on Application Security and advancing the maturity of the Software Security Development Lifecycle (SSDLC). He has led the development of AppSec programs for international corporations, including initiatives in software supply chain security, Threat modeling, and Security Champions programs.

Nariman is a core team member of the OWASP SAMM (Software Assurance Maturity Model) project and holds the ISC2 Certified Secure Software Lifecycle Professional (CSSLP) certification.

Requirements:

Participants can bring their laptops in order to follow along with SAMM assessment, but it's not a requirement. Mostly the session will be interactive