Artificial Intelligence Trustworthiness and Risk Assessment Scientific Seminars
Artificial intelligence (AI) has already become a transformative technology that is having revolutionary impact in nearly every domain from business operations to more challenging contexts such as civil infrastructure, healthcare and military defense. AI systems built on large language and foundational/multi-modal models (LLFMs) have proven their value in all aspects of human society, rapidly transforming traditional robotics and computational systems into intelligent systems with emergent, beneficial and even unanticipated behaviors. However, the rapid embrace of AI-based critical systems introduces new dimensions of errors that induce increased levels of risk, limiting trustworthiness. Furthermore, the design of AI-based critical systems requires proving their trustworthiness. Thus, AI-based critical systems must be assessed across many dimensions by different parties (researchers, developers, regulators, customers, insurance companies, end-users, etc.) for different reasons. We can call it AI testing, validation, monitoring, assurance, or auditing, but the concept in all cases is to make sure the AI is performing well within its operational design and avoids unanticipated behaviors and unintended consequences. Such assessment begins from the early stages of research, development, analysis, design, and deployment. Thus, trustworthy AI systems and methods for their assessment should address full system-level functions as well as individual AI-models and require a systematic design both during training and development phases, ultimately providing assurance guarantees. At the theoretical and foundational level, such methods must go beyond explainability to deliver uncertainty estimations and formalisms that can bound the limits of the AI; find blind spots and edge-cases; and incorporate testing for unintended use-cases, such as adversarial testing and red teaming in order to provide traceability, and quantify risk. This level of performance is critically important to contexts that have highly risk-averse mandates such as, healthcare, essential civil systems including power and communications, military defense, and robotics that interface directly with the physical world.
These monthly online seminars of two hours, open to all, are a platform for discussions and explorations expected to ultimately contribute to the development of innovative solutions for quantitatively trustworthy AI.
Jun 17, 2026
4:00 pm - 5:00 pm (GMT)
4:00 – 5:00 PM CET, Jakob Rehof, Hercules and the Hydra. Lamarr Perspectives on Ensuring Trustworthy AI.
May 20, 2026
4:00 pm - 5:00 pm (GMT)
4:00 – 5:00 PM CET, Preben M. Ness, Causal Neural Networks for Robust Generalisation
Apr 15, 2026
4:00 pm - 5:00 pm (GMT)
4:00 – 5:00 PM CET, Laurent Desmet, (Schaeffler), Robust AI for Virtual Sensors
Mar 18, 2026
4:00 pm - 6:00 pm (GMT)
4:00 PM CET Matt J. Kusner, École Polytechnique de Montréal, An Auditing Test to Detect Behavioral Shift in Language Models
5:00pm CET Lionel Briand, University Ottawa, Automated Testing and Safety Analysis of Deep Learning Systems
Feb 18, 2026
4:00 pm - 5:00 pm (GMT)
4:00pm-5:00pm: Causality, why it matters in industrial context, Marianne Clausel, Simul Research Group@CRAN
Jan 21, 2026
4:00 pm - 5:00 pm (GMT)
4:00pm-5:00pm: The AI4REALNET project: Preliminary Results and Future Perspective, Milad LEYLI-ABADI, IRT SystemX
Dec 12, 2025
3:00 pm - 5:00 pm (GMT)
3:00pm-4:00pm: On the Trustworthy AI Dimensions Fairness, Confidentiality and Transparency and Their Dependencies, Cor Veenman, TNO
4:00pm-5:00pm: TBA
Nov 6, 2025
12:00 am - (GMT)
The ATRACC Symposium under AAAI Fall Symposium Series
Oct 15, 2025
4:00 pm - 6:00 pm (GMT)
4:00pm-5:00pm: “AI4Science: From Equations to Learning Machines”, Patrick Gallinari
5:00pm-6:00pm: “PRIV-LOC: Assessing and Mitigating Privacy Risks of Vision-Language Models in Image-based Geolocation Systems”, Shoaib Ehsan
Sep 10, 2025
4:00 pm - 6:00 pm (GMT)
4:00pm-5:00pm: Katell Lagatu, “Control strategy for actuator fault tolerance using deep reinforcement learning – Application to autonomous underwater UAVs”
5:00pm-6:00pm: TBA
Jul 23, 2025
4:00 pm - 6:00 pm (GMT)
4:00pm-5:00pm: “A multistream multimodal foundation model for real-time voice-based applications”, Patrick Perez
5:00pm-6:00pm: “Engineering Safe and Socially-Aware AI Systems”, Amel Bennaceur
Jun 18, 2025
4:00 pm - 6:00 pm (GMT)
4:00pm-5:00pm: Mattheos Fikardos, “Trustproofer: An agentic neuro-symbolic framework for operationalising AI trustworthiness”
5:00pm-6:00pm: Frédéric Barbaresco, “Trustworthy AI based on Analytical-Model Informed Machine Learning”
May 21, 2025
4:00 pm - 6:00 pm (GMT)
4:00pm-5:00pm: An Inductive Modeling of Distribution Shifts Enhances Trustworthy AI
5:00pm-6:00pm: safe.trAIn – Safe AI for driverless regional trains.
Apr 23, 2025
4:00 pm - 6:00 pm (GMT)
4:00 PM CET Alberto Bosio, EC Lyon, Trustworthy AI: The role of the Hardware
5:00pm CET Antoine Gautier, QuantPI, A unifying approach for performance bias and robustness testing in AI
Mar 26, 2025
4:00 pm - 6:00 pm (GMT)
4:00pm Shuang Ao, University of Southampton
Title: Safe and Trustworthy AI: Enhancing Uncertainty Quantification, Failure Detection,and Safety Alignment in LLMs and LVLMs
5:00pm Martin Gonzalez and Karla Quintero, IRT SystemX and Confiance.ai
Title : Leveraging Tropical Algebra to Assess Trustworthy AI
Feb 26, 2025
4:00 pm - 6:00 am (GMT)
4:00pm AI Safety: LLMs, Facts, Lies, and Agents in the Real World, by Christopher Pal, Professor, Polytechnique Montréal & Mila
5:00pm Automating Assessments of AI Systems by Daniel Becker, Fraunhofer IAIS
Jan 23, 2025
4:00 pm - 6:00 pm (GMT)
The first edition will start with a presentation of the supporting programmes. Future sessions will mainly contain scientific talks and discussions.
4:00pm CET Introduction of the supporting programmes
5:00pm CET Scientific seminar by Anita Prinzie, Datashift
Towards a deep integration of Trustworthy AI and AI Risk Management for all AI systems
A key collective of industrialists and academics is taking up the challenge of industrializing trustworthy artificial intelligence for critical systems. As a technological program of the French national AI strategy, Confiance.ai provides industrialists with an environment and tool-based methodologies to integrate AI components in their critical products and services
Confiance IA vient compléter l’écosystème québécois en IA par une approche de co- innovation appliquée aux besoins des entreprises. Des entreprises de secteurs d’activités différents partagent des cas d’usages génériques et conçoivent des outils pré-compétitifs et des méthodologies permettant de valider une IA de confianc
IVADO est un consortium interdisciplinaire et intersectoriel de recherche, de formation et de mobilisation des connaissances qui a pour mission de bâtir et de promouvoir une intelligence artificielle robuste, raisonnante et responsable. Piloté par l’Université de Montréal, avec 4 partenaires universitaires (Polytechnique Montréal, HEC Montréal, Université Laval et Université McGill), IVADO rassemble des centres de recherches, des partenaires gouvernementaux et industriels, pour coconstruire des initiatives intersectorielles ambitieuses favorisant un changement de paradigme de l’IA et de son adoption.
Together with the German Federal Office for Information Security (BSI) and the German Institute for Standardization (DIN) as well as other research partners, Fraunhofer IAIS is developing test procedures for the certification of artificial intelligence (AI) systems. The aim is to ensure technical reliability and responsible use of the technology. Industrial requirements are taken into account through the active involvement of numerous associated companies and organizations representing various industries such as telecommunications, banking, insurance, chemicals, and trade.
Responsible Ai UK will connect UK research into Responsible AI to leading research centres and institutions around the world. This will allow RAi UK to deliver world-leading best practices for how to design, evaluate, regulate, and operate AI-systems in ways that benefit people, society and the nation.
We’re Australia’s leading digital research network, helping our partners across business, government and industry solve real problems every day. Our projects cover a wide range of data-centric R&D
CERTAIN stands for "Centre for European Research in Trusted AI" and focuses on an approach that highlights the issue of "trust" in AI systems - an aspect that is often neglected in international research. The aim is to develop new technologies that provide functional and other guarantees for AI systems
The Ph.D. program in Intelligent Systems and Robotics is the first of its kind in the state of Florida, and among only a few in the nation preparing tomorrow’s thoughtleaders to transform the future of technology and society.
A not-for-profit research institute of the Florida University System and is affiliated with several Florida universities. Created at the University of West Florida, IHMC is home to teams investigating and refining artificial intelligence, augmentics, human-centered computing; robotics and exoskeletons; and health, resilience, and performance to maximize biological performance of humans in high-stress, extreme environments and disciplines
Join us as an official partner if your organisation is interested in Responsible AI research, innovation and skills. We are looking for partners including businesses, funders, charities, creative organisations, industry associations, think tanks and more. Find out more and sign up
RAi UK will store your data in accordance with the General Data Protection Regulation 2017 (GDPR). We will not share your data with any third parties and you are given opportunities to unsubscribe at any time within the electronic communications you receive, or by emailing info@rai.ac.uk