Friday, September 01, 2023 – Detailed

Time (UTC +2)
SA 1
Ground Floor
SA 2
Ground Floor
SA 3
First Floor
08:30 - 16:30
Organizers available
Conference Office - Ground Floor
09:00 - 10:15
Co-Director LSTS, Vrije Universiteit Brussel (VUB), Belgium
Session Chair:
Human-Centered AI Lab (Holzinger Group), University of Natural Resources and Life Sciences, Austria

CD-MAKE Keynote - Whiteboxing machine learning

The deployment of AI systems based on machine learning (ML) in real world scenarios faces a number of challenges due to its black box nature. The GDPR right to an explanation has given rise to frantic attempts to develop and design self-explanatory systems, meant to help people understand their decisions and behaviour. In this keynote I will explain (pun intended) why meaningful explanations require keen attention to the proxies used in ML research design. Once those confronted with the decisions or behaviour of ML systems have a better understanding of the pragmatic choices that must be made to allow a machine to learn, it will become easier to foresee what ML systems can and cannot do. Whiteboxing ML should focus on the proxies that stand for real world events, actions and states of affairs, highlighting that a proxy (dataset, variable, model) is not what it stands for.


10:15 - 10:45
Coffee Break
10:45 - 12:15
Performance and Trust
Session Chair:
Mireille Hildebrandt, Co-Director LSTS, Vrije Universiteit Brussel (VUB), Belgium
(joint session with SSE and IWSECC)
Session Chair:
Daniel Fraunholz, ZITiS, Germany
Vulnerability Detection
Session Chair:
Gianluca Lax, University of Reggio Calabria, Italy
12:15 - 13:15
Lunch Break
13:15 - 14:45
Hot Topics and Applications
Session Chair:
Andrea Campagner, IRCCS Istituto Ortopedico Galeazzi, Italy
(joint session with SSE and IWSECC)
Session Chair:
Simon Duque-Anton, Comlet Verteilte Systeme GmbH, Germany
14:45 - 15:00
Coffee Break