Introduction

The recent use of machine learning in high stakes applications has been pushing many industrial actors to rethink how safety-critical systems (such as planes or cars) can be certified before being manufactured and used. Key questions have emerged, such as: how to properly define safety of systems with learning components? how to formally guarantee safety? which new mathematical guarantees would be needed from the ML research community?

This workshop will bring together machine learning researchers with international authorities and industrial experts from sectors where certification and reliability is a critical issue. It will consist of invited talks, a poster session, and group discussions. The goal is to present key open industrial questions, traditional methods in critical software verification and certification (and AI-related challenges), as well as an introduction to several promising mathematical theories (distribution-free uncertainty quantification, deep learning theory, formal methods, and rigorous numerics).

This workshop is organized by the DEEL project. We hope this workshop will help shape the future research agenda toward the middle-term objective of certifying critical systems involving AI components.

Call for posters

Submit your poster proposal Author Instructions

Our workshop has a dedicated poster track. This session offers a unique opportunity to showcase advanced research towards certification of critical AI-based systems. Encouraged topics for contributions include probabilistic risk assessment, formal methods for neural networks, distribution-free uncertainty quantification, generalization guarantees for deep learning, robustness to adversarial attacks, distributional shift or model-misspecification, among others.

Key dates:

You are invited to submit your poster proposal (in the form either of a ready-to-go poster or of an extended abstract) using the Submit your poster proposal button. All accepted posters will be presented virtually during the workshop and posted on the website. Authors will also be encouraged to record a 3 min video that will be made public prior to the poster session.

Please check the instructions for authors for more details about the expected content and format.

Schedule

Schedule (to be confirmed). Time is given in UTC+1 (local time in Toulouse).

Day Time Speaker(s) Event
January 14, 2021 14:45–15:00 Organization team Opening remarks
15:00–15:50 Guillaume Soudain The Challenges of Certifying AI Solutions in Aviation
15:50–16:30 TBD Generalization guarantees for neural networks
16:30–16:45 Virtual coffee break
16:45–17:30 Poster Session
17:30–18:10 Aaditya Ramdas (TBC) Distribution-free Uncertainty Quantification for Black-box ML Algorithms
18:10–19:00 Group discussions Which Statistical Guarantees Should we Develop for AI Certification Purposes?
January 15, 2021 14:00–14:40 Antoine Miné Abstract Interpretation for Verification of Critical Embedded Software
14:40–15:20 Martin Vechev Abstract Interpretation for Certification of Neural Networks
15:20–15:30 Virtual coffee break
15:30–16:20 Group discussions Which Formal Methods Should We Develop for AI Certification Purposes?
16:20–17:00 Mioara Joldes Rigorous Numerics: A Short Introduction and Recent Challenges
17:00–17:40 Matthieu Cord Explainability of Vision-based Autonomous Driving Systems: Recent Work and Challenges
17:40–18:00 Sébastien Gerchinovitz Summary of Future Research Directions

Registration

Register Now

Registration to the workshop is free but mandatory. Please click the above button.

Talks

The Challenges of Certifying AI Solutions in Aviation

Abstract Interpretation for Verification of Critical Embedded Software

Abstract Interpretation for Certification of Neural Networks

Rigorous Numerics: A Short Introduction and Recent Challenges

People

This workshop is organized by the DEEL project

Invited Speakers

Avatar

Aaditya Ramdas (TBC)

Assistant Professor in Statistics and Machine Learning

Carnegie Mellon University

Avatar

Antoine Miné

Professor in Computer Science

Sorbonne University

Avatar

Guillaume Soudain

Critical Software Senior Expert

European Union Aviation Safety Agency (EASA)

Avatar

Martin Vechev

Professor in Computer Science

ETH Zurich

Avatar

Matthieu Cord

Professor in Computer Science

Sorbonne University & Part-time Principal Scientist at valeo.ai

Avatar

Mioara Joldes

Researcher in Computer Science

LAAS - CNRS

Organizers

Avatar

Adrien Gauffriau

Critical Avionics Software Engineer

Airbus

Avatar

Baptiste Lefevre

Advanced Technologies Regulation Manager

Thales

Avatar

Foutse Khomh

Professor in Computer Science

Polytechnique Montreal

Avatar

Francois Laviolette

Professor in Artificial Intelligence

University of Laval

Avatar

Mélanie Ducoffe

Research Engineer

Airbus

Avatar

Sébastien Gerchinovitz

Research Scientist

IRT Saint-Exupery & University of Toulouse

Additional Program Committee

Avatar

Edouard Pauwels

Assistant Professor in Mathematics and Computer Science

Institut de Recherche en Informatique de Toulouse

Avatar

Franck Mamalet

Research Scientist

IRT Saint-Exupery

Avatar

Giuliano Antoniol

Professor of Software Engineering

Polytechnique Montréal

Avatar

Gregory Flandin

DEEL Program Director

IRT Saint-Expuery

Avatar

Jean-Michel Loubes

Professor of Mathematics

Institut de Mathématiques de Toulouse

Avatar

Mathieu Serrurier

Assistant Professor in Computer Science

Institut de Recherche en Informatique de Toulouse