Track A: Trusted AI
The development of Deep Learning has transformed AI from a niche science into a socially relevant “mega-technology”. At the same time, it raises a range of problems, such as the lack of internal representation of meaning (interpretability), sensitivity to changes in the input (robustness), lack of transferability to unseen use cases (generalizability), potential discrimination and biases (fairness) and, finally, the big data hunger itself (data efficiency). Recently, a new overall approach to solving these problems has been pushed forward under the term “Trusted AI” or “Trustworthy AI”. The Trusted AI track will cover the latest advances in this area.
Timetable – Speaker
Mon, August 29, 2022
Opening Speech – 13:15-14:15
Course 1 – 14:30-17:15Catuscia Palamidessi and Sayan Biswas (Inria)
Catuscia Palamidessi is Director of Research at Inria Saclay. She has been Full Professor at the University of Genova and Penn State University. Palamidessi’s research interests include Machine Learning, Privacy, Fairness, Secure Information Flow, and Concurrency. In 2019 she obtained an Advanced Grant from the European Research Countil for the project “Hypatia”, which focuses on identifying methods for local differential privacy offering an optimal trade-off with quality of service and statistical utility. She is in the Editorial board of various journals, including the IEEE Transactions on Dependable and Secure Computing, the Journal of Computer Security, Mathematical Structures in Computer Science, and Acta Informatica. She is member of the advising committee of the French National Information Systems Security Agency (ANSSI).
Sayan Biswas is a second-year doctoral candidate at Inria Saclay and Ecole Polytechnique in France being supervised by Catuscia Palamidessi. Born and raised in Kolkata, India, Sayan obtained his undergraduate and master’s degree with first-class honours from University of Bath in the UK, where he specialized in probability theory and statistics. He has been participating in mathematics and competitive programming contests and olympiads from a very young age. His present research interests include differential privacy, privacy-utility optimization, privacy-preserving machine learning, and federated learning.
Privacy and fairness
Tue, August 30, 2022
Keynote 1 – 09:00-10:00Michael Luck (King's College London)
Michael Luck is Professor of Computer Science in the Department of Informatics at King’s College London, where he also works in the Distributed Artificial Intelligence group, undertaking research into agent technologies and artificial intelligence. He is currently Director of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence, Director of the King’s Institute for Artificial Intelligence, and scientific advisor for Aerogility, ContactEngine and CtheSigns. He is co Editor-in-Chief of the journal, Autonomous Agents, and Multi-Agent Systems, and is a Fellow of the European Association for Artificial Intelligence and of the British Computer Society.
Artificial Intelligence: Towards safety and trust
|Course 2 – 10:30-13:15
Vera Sosnovik is a third-year PhD student at University Grenoble Alpes working with Dr Oana Goga. She graduated from University Grenoble Alpes in 2019 with a Master Degree in Data Science. Her work focuses on detecting and studying problematic ads in social media and assesses the impact they have on users.
Salim Chouaki is a second year PhD student at University Grenoble Alpes. He graduated in 2020 with an engineering degree in computer systems and software. He works on analysing risks associated with incidental and targeted exposure to information on social media using the CheckMyNews chrome extension that he has developed to collect data from Facebook.
Security and privacy issues with social computing and online advertising The enormous financial success of online advertising platforms is partially due to the precise targeting features they offer. Ad platforms collect a large amount of data on users and use powerful AI-driven algorithms to infer users’ fine-grain interests and demographics, which they make available to advertisers to target users. In the lab, we will work on code to collect data from public online advertising APIs and build algorithms to analyse this data.
The enormous financial success of online advertising platforms is partially due to the precise targeting features they offer. Ad platforms collect a large amount of data on users and use powerful AI-driven algorithms to infer users’ fine-grain interests and demographics, which they make available to advertisers to target users.
In the lab, we will work on code to collect data from public online advertising APIs and build algorithms to analyse this data.
|Course 3 – 15:45-18:30
Caterina Urban (Inria)
Caterina is a research scientist in the Inria research team ANTIQUE (ANalise StaTIQUE), working on static analysis methods and tools to enhance the reliability and our understanding of data science and machine learning software. She is Italian and studied for her Bachelor’s (2009) and a Master’s (2011) degree in Computer Science at the University of Udine. She then moved to France and completed her Ph.D. (2015) in Computer Science, working under the joint supervision of Radhia Cousot and Antoine Miné at École Normale Supérieure. Before joining Inria (2019), she was a postdoctoral researcher at ETH Zurich in Switzerland.
Formal methods for machine learning
Wed, August 31, 2022
Keynote 2 – 09:00-10:00Sophie Quinton (Inria)
Sophie Quinton is a research scientist in computer science at INRIA in Grenoble, France. Her research background is on formal methods for the design and verification of embedded systems, with an emphasis on real-time aspects. She is now studying the environmental impact of ICT, in particular on claims about the benefits of using digital technologies for GHG emissions mitigation.
ICT and sustainability
|Course 4 – 10:30-13:15
Martin Georg Fränzle (University of Oldenburg)
Martin Fränzle has been the Professor for Hybrid Systems within the Department of Computing Science at the University of Oldenburg since 2004 and for Foundations and Application of Systems of Cyber-Physical Systems since 2022. He holds a diploma and a doctoral degree in Computer Science from Kiel University and was Associate Professor (2002-2004) and Velux Visiting Professor (2006-2008) at the Technical University of Denmark (DTU), Dean of the School of Computing Science, Business Administration, Economics, and Law at Oldenburg, and recently the Vice President for Research, Transfer, and Digitalization at the University of Oldenburg. His research spans a scope from fundamental research, in particular dynamic semantics and decidability issues of formal models of cyber-physical systems, over technology development addressing tools for the modelling, automated verification, and synthesis of cyber-physical and human-cyber-physical system designs to applied research as well as technology transfer with automotive and railway industries as well as design-tool vendors, the latter being based on numerous industrial cooperation projects.
AI components for high integrity, safety-critical cyber-physical systems: chances and risks
|Course 5 – 15:45-18:30
André Meyer-Vitali (DFKI)
Dr. André Meyer-Vitali is a computer scientist who got his Ph.D. in software engineering and distributed AI from the University of Zürich. He worked on many applied research projects on multi-agent systems at Philips Research and TNO (The Netherlands) and participated in AgentLink. He also worked at the European Patent Office. Currently, he is a senior researcher at DFKI (Germany) focused on engineering and promoting Trusted AI and is active in the AI networks TAILOR and CLAIRE. His research interests include Software und Knowledge Engineering, Design Patterns, Neuro-Symbolic AI, Causality, and Agent-based Social Simulation (ABSS) with the aim to create Trust by Design.
Trustworthy hybrid team decision-support
Thu, Sep 01, 2022
Keynote 3 – 09:00-10:00Marcus Voß (Birds on Mars)
Marcus Voß is an AI Expert and Intelligence Architect at Birds on Mars, where he works on AI applications for sustainable use cases. He is an external lecturer on AI and data science at TU Berlin and CODE University of Applied Sciences. Previously, he was a Research Associate at TU Berlin, where he led the research group “Smart Energy Systems” at the DAI Lab. He is active as Community Lead for the building and transportation sector at Climate Change AI, an international initiative that brings together stakeholders around AI and climate change.
Applying Artificial Intelligence for climate action
|Course 6 – 10:30-13:15
Freddy Lecue (Thales & Inria)
Freddy Lecue is the Chief AI Scientist at CortAIx (Centre of Research & Technology in AI eXpertise) at Thales in Montreal – Canada. He is also a research associate at Inria, in WIMMICS, Sophia Antipolis – France. Before joining the new R&T lab of Thales dedicated to AI, he was AI R&D Lead at Accenture Labs in Ireland from 2016 to 2018. Prior joining Accenture he was a research scientist, lead investigator in large scale reasoning systems at IBM Research from 2011 to 2016, a research fellow at The University of Manchester from 2008 to 2011 and research engineer at Orange Labs from 2005 to 2008. His research area is at the frontier of intelligent / learning and reasoning systems. He has a strong interest on Explainable AI i.e., AI systems, models and results which can be explained to human and business experts.
Explainable AI: a focus on machine learning and knowledge graph-based approaches
|Course 7 – 15:45-18:30
Titouan Vayer (ENS Lyon)
Titouan Vayer is currently a postdoctoral researcher at ENS Lyon and works on compressive learning problems. He worked during his thesis, which was obtained in 2020 in IRISA, Vannes, on optimal transport methods for machine learning: In particular in the context of graphs and heterogeneous data. Titouan Vayer is particularly interested in the theory of learning in complex settings where the data are large, structured and do not admit the same representation.
Less is more? How compressive learning and sketching for large-scale machine learning works
Fri, Sep 02, 2022
Course 8 – 09:00-12:00Rafaël Pinot (EPFL)
Rafaël is currently a postdoctoral researcher at EPFL working with Pr. Rachid Guerraoui and Pr. Anne-Marie Kermarrec within the Ecocloud Research Center. He holds a PhD in Computer Science from Université Paris Dauphine-PSL. His main line of research is in statistical machine learning and optimization with a focus on the security and privacy of machine learning applications. He is also interested in statistical analysis of complex data structures.
Are neural networks getting smarter? State of knowledge on adversarial examples in machine learning Collaborative Wrap-Up – 12:15-13:15
Collaborative Wrap-Up – 12:15-13:15