Programme.
​08:45-09:00
Opening and welcome to WAISE 2023, Organisation Committee
Keynote Talk
​09:00-10:00
Challenges in Building Safe LLM-Powered Conversational Systems
Razvan Dinu, Principal Applied Scientist, NVIDIA
​10:00-10:30
Coffee break
Session 1: AI Uncertainty and Monitoring
​10:30-10:50
Contextualised Out-of-Distribution Detection using Pattern Identification
Romain Xu-Darme, Julien Girard-Satabin, Darryl Hond, Gabriele Incorvaia and Zakaria Chihani
​10:50-11:10
Conformal Prediction and Uncertainty Wrapper: What Statistical Guarantees Can You Get for Uncertainty Quantification in Machine Learning?
Lisa Jöckel, Michael Klaes, Janek Groß and Pascal Gerber
​11:10-11:30
AERoS: Assurance of Emergent Behaviour in Autonomous Robotic Swarms
Dhaminda Abeywickrama, James Wilson, Suet Lee, Greg Chance, Peter Winter, Arianna Manzini, Ibrahim Habli, Shane Windsor, Sabine Hauert and Kerstin Eder
Session 2: Assurances for Autonomous Systems
​11:30-11:45
Towards Deep Anomaly Detection with Structured Knowledge Representations (Doctoral paper)
Konstantin Kirchheim
​11:45-12:00
A Reasonable Driver Standard for Automated Vehicle Safety
Philip Koopman and William Widen
​12:00-13:00
Lunch break
Session 3: AI Safety
​13:00-13:20
Safety Integrity Levels for Artificial Intelligence
Simon Diemert, Laure Millet, Jonathan Groves and Jeffrey Joyce
​13:20-13:40
AIMOS: Metamorphic Testing of AI - An Industrial Application
Augustin Lemesle, Aymeric Varasse, Zakaria Chihani and Dominique Tachet
​13:40-14:00
A Group-Level Learning Approach Using Logistic Regression For Fairer Decisions
Marc Elliott and Deepak Padmanabhan
Session 4: Assurances for Autonomous Systems 2
​14:00-14:20
Towards Safe Machine Learning Lifecycles with ESG Model Cards
Thomas Bonnier and Benjamin Bosch
​14:20-14:40
Can Large Language Models assist in Hazard Analysis?
Simon Diemert and Jens Weber
​14:40-15:00
Short Birds of a Feather Session
​15:00-15:30
Coffee break
Session 5: AI Safety 2
​15:30-15:45
Evaluating and Increasing Segmentation Robustness in CARLA
Venkatesh Sambandham, Konstantin Kirchheim and Frank Ortmeier
​15:45-16:00
Structuring Research Related to Dynamic Risk Management for Autonomous Systems
Rasmus Adler, Jan Reich and Richard Hawkins
Community Debate
16:00-17:00
Plenary Discussion "Is the Last Mile in Engineering Safe AI Systems LLM-based?"
​17:00-17:10
WAISE2023 Wrap Up