Programme.
Keynote Talk (Chair: Chih-Hong Cheng)
​09:00-10:00
The Road to Trustworthy AI
​10:00-10:30
Coffee break
Session 1. (Chair: Orlando Avila-García)
​10:30-10:50
A Modular AI Testing Framework for Trustworthy AI: Proof-of-Concept Implementation
Maximilian Pintz, Daniel Becker and Michael Mock
​10:50-11:10
Safe Adversarial Control Through Interaction
Benedikt Rank and Mario Trapp
​11:10-11:30
Does not impute! Performance and ethical implications of missing data for an AI-based diabetes co-morbidity predictor
Philippa Ryan, Berk Ozturk, Laura Fearnley, Tom Lawton and Ibrahim Habli
Session 2. (Chair: Jelena Frtunikj)
​11:30-11:50
Facilitating Fault Tree Analysis with Generative AI
Yujiao Shentu and Mario Trapp
​11:50-12:10
Risk Analysis of One-Pixel Image Defects in Safety-Critical Deep Neural Networks
Krystian Radlak, Adam Popowicz, Michal Szczepakiewicz and Paweł Zawistowski
​12:10-12:30
Efficient Safety Retrofitting Against Jailbreaking for LLMs
Dario Garcia-Gasulla, Adrian Tormos, Anna Arias-Duart, Daniel Hinjos, Oscar Molina-Sedano, Ashwin Kumar Gururajan and Maria Eugenia Cardello
​12:30-13:30
Lunch break
Session 3 (Chair: Philippa Ryan)
​13:30-13:50
Uncovering Unsafe Feature Interactions in Vehicle Control Using Generative AI and Digital Twins
Laure Millet, Justin Kernot, Arun Adiththan, Ramesh S, Rami Debouk and Jeffrey Joyce
​13:50-14:10
AURORA Networks: Auto-associative Universal Real-time Outlier Risk Assessment Networks
Moritz Zink, Daniel Grimm and Eric Sax
​14:10-14:30
Architectural Mitigation of Control AI Risk Factors for Safe Human-Robot-Collaboration
Andreas Kreutz, René Beck, Gereon Weiss and Satoshi Otsuka
Session 4 (Chair: Chih-Hong Cheng)
​14:30-14:50
Runtime Safety Engineering for AI Robotics: Lessons from Scaling Trust at Amazon
Gianpiero Negri
​14:50-15:10
HySAFE-AI: Hybrid Safety Architectural Analysis Framework for AI Systems
Mandar Pitale, Jelena Frtunikj, Abhinaw Priyadershi, Vasu Singh and Maria Spence
​15:10-15:30
The BIG Safety Argument
Ibrahim Habli
​15:30-16:00
Coffee break
Community Debate (Chair: Orlando Avila-García)
​16:00-16:50
​16:50-17:00
Plenary Discussion: "Safety Alignment, Foundation Models and GenAI - Yin and Yang"
WAISE 2025 Wrap Up