Bandeau image
DATAIA DAYS Safety and AI 11th of September

DATAIA DAYS ON SAFETY & AI

DATAIA DAYS ON SAFETY & AI

Chapo
First DATAIA DAYS on SAFETY & AI September 11th, 2019

SAFETY IN AI SHOULD NOT BE AN OPTION, BUT A DESIGN PRINCIPLE
Contenu
Corps de texte

Organizers: Pablo Piantanida (CentraleSupélec), Francois Terrier  (CEA List) & Digicosme

Co-organizer : Labex Digicosme

This DATAIA Day will explore new ideas on Artificial Intelligence (AI) and safety engineering to develop rigorous techniques for building safe and trustworthy AI autonomous systems and establishing confidence in their behavior and robustness, thereby facilitating their successful adoption in society. Safety in AI should not be an option, but a design principle. However, there are different levels of safety and different degrees of liability, for which we face trade-offs or alternative solutions. These choices can only be analyzed if we consider both the theoretical and practical challenges of the engineering problem for AI safety. This view must cover a wide range of AI paradigms, including systems that are specific for a particular application, those that are more general, and can lead to unanticipated potential risks. We must also bridge short-term with long-term issues, idealistic with pragmatic solutions, operational with policy issues, and industry with academia, to really build, evaluate, deploy, operate and maintain AI-based systems that are truly safe.

In particular, SAFETY-DATAIA will provide a forum for thematic presentations and in-depth discussions about safe AI architectures, ML safety, safe human-machine interaction, and safety considerations in automated decision-making systems, in a way that makes AI-based systems more trustworthy. SAFETY-DATAIA  aims at bringing together experts, researchers, and practitioners, from diverse communities, such as AI, safety engineering, ethics, standardization and certification, robotics, cyber-physical systems, safety-critical systems, and application domain communities such as automotive, healthcare, manufacturing, agriculture, aerospace, critical infrastructures, and retail.

Program

09h00 - 09h30    Welcome Coffee

09h30 - 09h45    Opening Speech - Bertrand Thirion (DATAIA), Pablo Piantanida (CentraleSupelec) & François Terrier (CEA List)
09h45 - 10h30    Keynote  Rob Ashmore (UK Defense Science & Technology Laboratory) - Assuring the Machine Learning Lifecycle

10h30 - 10h45      Coffee Break

10h45 - 11h15      Machine Learning & Privacy : friends or enemies ? -  Catuscia Palamidessi (Inria, LIX)
11h15 - 11h45    Randomization techniques for robustness to adversarial attacks - Jamal Atif (Paris Dauphine), Cédric Gouy-Pailler (CEA List) & Rafaël Pinot (Paris Dauphine PSL & CEA)
11h45 - 12h15      Formal  validation  for  machine  learning - Zakaria Chihani, Julien Girard (CEA List)  & Guillaume Charpiat, Marc Schoenauer (LRI/INRIA)
 
12h15 - 14h15    Lunch Break

14h15 - 14h45      Explainability for machine learning - Frédéric Pascal, Pablo Piantanida (CentraleSupélec)
14h45 - 15h15     Safety evaluation process for AI based autonomous systems - Morayo Adedjouma & Gabriel Pedroza (CEA List)

15h15 - 15h30     Coffee Break

15h30 - 16h00    Javier Ibanez-Guzman, Autonomous Vehicule Expert (Renault)
16h00 - 16h30     David Sadek, Trust on AI (Thalès)
16h30 - 17h30     Roundtable – « Safety of AI, Industrial Challenges» :
        - Moderator : Jean-Noel Patillon (Director of CEA List, AI program coordinator at CEA Tech)
          - Guests :
            - Julien Chiaroni, Director, Grand Défi
            «Sécurisation, certification et fiabilisation de l’intelligence artificielle»
            - Javier Ibanez-Guzman, Autonomous Vehicule Expert (Renault)
            - Michaël Krajecki, Director of AI program (Agence de l’innovation pour la                 Défense)
            - David Sadek,  Vice President, Research, Technology & Innovation (Thalès)
17h30 - 18h00     Next steps ( Pablo Piantanida, François Terrier & Bertrand Thirion)

18h00 - 18h45    Closure Cocktail

Registrations are closed