Robust Artificial Intelligence

- Online -

11 - 14 January 2021

Venue: Lorentz Center@Virtual

If you are invited or already registered for this workshop, you have received login details by email.

As industry moves towards more inclusion of AI in its products, there is a crucial need to investigate how academic and industrial research can contribute to the robustness assessment of AI in safety-critical systems. The present workshop aims at updating the community on the state-of-the-art in “Robustness in AI”, discussing how it aligns with industrial challenges and discuss a more collaborative future on AI safety between research institutes and industries.

It will specifically focus on:

  • AI robustness assessment against unexpected/adversarial perturbations

  • Formal and probabilistic methods for the verification of AI models.

  • Compatibility, adaptability and scalability of current techniques to industrial problematics, potential limitations

  • Ways forward towards their use in safety-critical systems.

Read more...

    Monday 11 January 2021

    Start ~ 4:00 pm (CET time) - Time slots below show time since start of the day (00:00).

    4h00 - Theme: Real-life applications - Industrial use cases

    To follow this session, participants are invited to look at pre-recorded reviews on ‘industrial challenges’. All domain reviews will (ideally) follow a common format:
    1- AI-driven use cases 2- challenges 3- current envisioned solutions 4- world-wide initiatives

    00:0000:10 Welcomes by the Lorentz Center and organising committee
    00:1000:35 Recap + Q&A on robustness of AI in the aeronautics domain
    00:3501:03 Break
    00:3501:02 Recap + Q&A: Law and AI
    00:3501:01 Recap + Q&A on robustness of AI in the healthcare domain
    02:0004:00 Break-out session: Theme: Aligned/diverging industrial AI robustness challenges. AI shortcomings. Short-, mid-, long-term solutions
    02:0002:30 Introduction (panel)
    02:3003:00 Break-out session / Brainstorming - Participants separated in discussion groups (x 3)
    03:0004:00 Debriefing break-out session + panel discussion

    Tuesday 12 January 2021

    Start ~ 4:00 pm (CET time) - Time slots below show time since start of the day (00:00).

    4h00 - Theme: Robustness against unexpected or adversarial conditions

    Empirical approaches to AI robustness assessment

    To follow this session, participants are invited to view pre-recorded reviews/talks on ‘Empirical robustness’.
    Reviews and talks are expected to go beyond the introduction of state-ot-the-art AI robustness techniques and focus on
    their limitations and envisioned extensions and research ways forward.

     

    00:0001:00 Flash talks recap + Q&A on pre-recorded reviews and talks
    01:0004:00 

    Break-out session 
    Themes: Adversarial attacks: a true threat to real-life applications? - How can empirical verification be used in an industrial qualification/certification framework? 

    01:0004:00 

    Break-out session:

    Where lies the balance between AI architecture complexity and vulnerability to attacks?

    01:0001:30 Introduction (panel)
    01:3002:00 Break-out session / Brainstorming - Participants separated in discussion groups (x 3)
    02:0002:15 Break
    02:1503:15 Debriefing break-out session + panel discussion
    03:1504:00 Library SW demonstration: Adversarial ML

    Wednesday 13 January 2021

    Start ~ 4:00 pm (CET time) - Time slots below show time since start of the day (00:00).

    4h00 - Theme: Formal assessment of robustness

    To follow this session, participants are invited to view pre-recorded reviews/talks on 'Formal robustness'

    Reviews and talks are expected to go beyond the introduction of state-ot-the-art AI robustness techniques and focus on their limitations and envisioned extensions and research ways forward.

    00:0001:00 Flash talks recap + Q&A on pre-recorded reviews and talks
    01:0004:00 Break-out session Themes: Scalability - Complementarity of techniques?
    01:0001:30 Introduction (panel)
    01:3002:00 Break-out session / Brainstorming - Participants separated in discussion groups (x 3)
    02:0002:15 Break
    02:1503:15 Debriefing break-out session + panel discussion
    03:1504:00 Library/SW demonstration: Formal methods #1
    03:1504:00 Library/SW demonstration: Formal methods #2 (parallel)

    Thursday 14 January 2021

    Start ~ 4:00 pm (CET time) - Time slots below show time since start of the day (00:00).

    2h30 - Discussions, conclusions & ways forward

    00:0001:00 

    Panel discussion 1: Theme: "How will current and future research on robustness assessment techniques solve AI industrial challenges?"

    01:0001:45 

    Panel discussion 2 Theme: "Ways forward & research road map"

    01:4502:00 

    Panel discussion 3 Theme: "Future collaboration: Favored means & platforms?"

    02:0002:30 

    Panel discussion 4 Theme: "The workshop legacy"

    Please log in to view the participants information...

    Audrey Galametz, Airbus  

    Babette Bakker, TNO  

    Joseph Nagel, Airbus SE  

    Mélanie Ducoffe, Airbus SAS  

    Jayant Sen Gupta, Airbus SAS  

    Joris Sijs, TNO  


Maria Krebbers

+31 71 527 5578

krebbers@lorentzcenter.nl

Follow us on:

Niels Bohrweg 1 & 2

2333 CA Leiden

The Netherlands

+31 71 527 5400