Announcement  of first ATRASS, Jan 23, 4:00pm CET

The first online  “ATRASS”: AI Trustworthiness and Risk Assessment  Scientific Seminar, will be held on 23 Jan 2025, 4:00pm CET, following the successful ATRACC (AI Trustworthiness and Risk Assessment for Challenged Contexts) symposium held in Arlington, VA, last November.

This monthly online seminar, open to all, will contain scientific presentations of interest for the community of researchers and practitioners of the domain. The sessions will be recorded and published for later viewing.

The first edition will start with a presentation of the supporting programmes. Future sessions will mainly contain scientific talks and discussions.

Agenda:

• 4:00pm CET Introduction of the supporting programmes (10 minutes each):
  • CERTAIN by DFKI
  • Confiance.ai by IRT SystemX
  • IVADO/Confiance.ia qc by Polytechnique Montreal
  • Responsible AI UK by University of Southampton
  • UWF programme by University West Florida
  • Zertifizierte KI by Fraunhofer IAIS
• 5:00pm CET Scientific seminar by Anita Prinzie, Datashift
  • Towards a deep integration of Trustworthy AI and AI Risk Management for all AI systems
  • Abstract: Trustworthy AI and AI Risk Management share the common goal of ensuring that AI systems can be trusted, yet they approach this objective through distinct but compatible methods. This presentation explores the core principles of Trustworthy AI and AI Risk Management, highlighting the complementarity of these two domains, which have largely developed independently. We argue for the benefits of deeply integrating Trustworthy AI and AI Risk Management across all AI systems, not limited to high-risk applications mandated by the AI Act. Finally, we outline a vision for achieving this integration, addressing the scientific challenges that must be overcome to create a unified framework.

To know more about ATRACC, visit AAAI 2024 FS – ATRACC (google.com)