ELSA Strategic Research Agenda: Facing the Grand Challenges of Secure and Safe AI
ELSA Strategic Research Agenda: Facing the Grand Challenges of Secure and Safe AI
The Strategic Research Agenda (SRA) delineates ELSA's vision, strategic objectives and research approach towards ensuring secure and safe AI. The initial version (SRA v1.0) is built on the following 3 deliverables of the ELSA network: D1.1 Grand Challenge Report: Technical Robustness and Safety Grand Challenge and Benchmarking MetricsLead authors: Ambra Demontis, Angelo Sotgiu, Maura Pintor, Battista Biggio; Contributors: Marta Kwiatkowska, Xiyue Zhang, Luca Oneto, Fabio Roli, Mario Fritz, Tatiana tommasi D2.1 Report on Privacy and Infrastructures Grand Challenge and Benchmarking MetricsLead authors: Antti Honkela; Contributors: Nicolò Cesa-Bianchi, Martin Jaggi, Catuscia Palamidessi, Massimiliano Pontil, Juliette Achdou, Joonas Jälkö, Raouf Kerkouche, Kangsoo Jung, Mario Fritz D3.1 Grand Challenge Report: Human-in-the-loop decision making: integrated governance to ensure meaningful oversightLead Authors: Plamen Angelov, Dmitry Kangin, Umang Bhatt, Karen Yeung, Rotem Medzin; Contributors: Mario Fritz, Dimosthenis Karatzas,Ruben Perez Tito, Mohamed Soubgui, Vincent d’Andecy, Patrick Perez, Battista Biggio The Strategic Research Agenda is set to be constantly updated and enhanced through close collaboration between ELSA's Executive Board and its Ethics, Industrial and Scientific Committees. ELSA actively seeks and welcomes input and contributions from the larger research community.
- University of Cagliari Italy
- Helmholtz Center for Information Security Germany
- Lancaster University United Kingdom
- University of Helsinki Finland
- Computer Vision Center Spain
Cybersecurity, Robotics, Trustworthy AI, Autonomous Driving, Machine Learning, Human Oversight, Large Language Models, Human in the loop, Multimedia, Agency, Artificial Intelligence, Privacy, Health, Security, Technical Robustness, LLMs, Safety, Robustness, AI Security, Integrated Governance, Document Intelligence
Cybersecurity, Robotics, Trustworthy AI, Autonomous Driving, Machine Learning, Human Oversight, Large Language Models, Human in the loop, Multimedia, Agency, Artificial Intelligence, Privacy, Health, Security, Technical Robustness, LLMs, Safety, Robustness, AI Security, Integrated Governance, Document Intelligence
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!