Programme.

(Timezone: CEST)

safecomp2022Workshop.png

​09:00-09:15

Opening and welcome to WAISE 2022, Organisation Committee

Keynote Talk

​09:15-10:30

Formal Methods for Trusted AI

Bettina Könighofer, Graz University of Technology, Austria

​10:30-11:00

Coffee break

Session 1: AI Safety

​11:00-11:20

Safe Design of Stable Neural Networks for Fault Detection in Small UAVs

Kavya Gupta, Fateh Kaakai, Beatrice Pesquet-Popescu and Jean-Christophe Pesquet

​11:20-11:40

A Neural Criticality Metric for Object Detection Deep Neural Networks

Václav Diviš, Tobias Schuster and Marek Hrúz

​11:40-12:00

StaDRe and StaDRo: Reliability and Robustness Estimation of ML-based Forecasting using Statistical
Distance Measures

Mohammed Naveed Akram, Akshatha Ambekar, Ioannis Sorokos, Koorosh Aslansefat and Daniel Schneider

Session 2: Advances in Safe AI (Invited talks)

​12:00-12:15

​12:15-12:30

​12:30-13:30

Lunch break

Session 3: Advances in Safe AI (Invited talks)

​13:30-13:45

Confiance.ai

Bertrand Braunschweig

​13:45-14:00

Session 4: Assurances for Autonomous Systems

​14:00-14:20

​14:20-14:40

Object Detection With Probabilistic Guarantees: a Conformal Prediction Approach

Florence de Grancey, Jean-Luc Adam, Lucian Alecu, Sébastien Gerchinovitz, Franck Mamalet
and David Vigouroux

​14:40-15:00

A Novel Abstraction Framework for Neural Network Verification

Fateh Boudardara, Abderraouf Boussif, Pierre-Jean Meyer and Mohamed Ghazel

​15:00-15:15

Logically Sound Arguments for the Effectiveness of ML Safety Measures

Chih-Hong Cheng, Tobias Schuster and Simon Burton

​15:15-15:45

Coffee break

Session 5: Community Debate

​15:45-16:45

​16:45-17:00

Plenary Discussion "Towards the Last Mile in Engineering Safe AI Systems"

WAISE2022 Wrap Up

awardhome.png