ELSA
This project ended in August 2026.
About
ELSA - the European Lighthouse on Secure and Safe AI connects excellent researchers from 26 top research institutions and companies in Europe to pool their expertise in the field of AI and machine learning, and to spearhead efforts in foundational safe and secure AI methodology research. The network builds on and extends ELLIS, and is coordinated by the CISPA Helmholtz Center for Information Security in Saarbrücken (Germany), which is part of the ELLIS Unit Saarbrücken.
Similar to ELLIS, it rests on three pillars: selected research programs, local research units, and a PhD and postdoc program. ELSA is funded under the European Union's Horizon Europe research and innovation program and will establish a fluid two-way communication between academic research and real-life application scenarios through the creation of the ELSA Innovation Lab.
ELSA received an extension and ran an additional year.
Network
Funding Partners
ELSA’s 26 founding members include European experts in all aspects of safe and secure AI, including technical robustness, privacy-preserving techniques and human agency and oversight. In addition, ELSA brings on board research and industry experts in six different sectors that are key application areas of safe and secure AI. They are the Cispa Helmholtz Center For Information Security, Computer Vision Center, European Molecular Biology Laboratory (EMBL), EPFL, ETH Zurich, Italian Institute of Technology, KTH Royal Institute of Technology, Lancaster University, Leonardo, Max Planck Society, National Institute for Research in Computer Science and Automation (Inria), National Interuniversity Consortium for Informatics (CINI), Polytechnic University of Turin, University of Cagliari, University of Genoa, University of Milano, NVIDIA, PAL Robotics, Pluribus One, Alan Turing Institute, University of Birmingham, University of Helsinki, University of Modena and Reggio Emilia, University of Oxford, Valeo and Yooz.
ELSA also expanded and welcomed 22 new associated members and partners: Czech Technical University in Prague, École normale supérieure (ENS-PSL), ELLIS Alicante, Instituto Superior Técnico, Instituto De Telecomunicações, Instituto de Engenharia de Sistemas e Computadores (INESC-ID), Institute For Systems And Robotics, Friedrich Schiller University Jena, IDEAS Research Institute, Artificial Intelligence Research Institute (IIIA-CSIC), Institute of Science and Technology Austria, Johannes Kepler University Linz, Max Planck Institute for Biogeochemistry, Radboud University, Graz University of Technology, Technical University of Darmstadt, TU Delft, Ukrainian Catholic University, University of Barcelona, University of Freiburg, Universitat Politècnica de Catalunya, and the Universitat Pompeu Fabra.
ELSA Strategic Research Agenda (SRA)
The increasingly pervasive deployment of AI systems, often built on machine learning, has highlighted the urgency of enforcing the principles of Trustworthy AI to ensure these systems work for the good of people and society. Achieving this goal requires societal and policy action, as well as research in technologies and social principles that enable it.
ELSA is a virtual center of excellence that builds upon the ELLIS network and spearheads efforts in foundational safe and secure AI methodology research addressing three major challenges: The development of robustness guarantees and certificates, privacy-preserving and robust collaborative learning, and the development of human control mechanisms for the ethical and secure use of AI with a focus on use cases in health, autonomous driving, robotics, cybersecurity, media and document intelligence.
ELSA is taking a foundational and interdisciplinary approach to these challenges that are characterized and outlined by the Strategic Research Agenda published in August 2023. You can download the full version via Zenodo.
An updated SRA will be published in 2026.
ELSA Benchmarks Platform
The platform provides a single access point to all ELSA Use Case-related resources (data, metrics, benchmarks) and allows participation in the ELSA competitions.
On the platform, users can browse the Use Cases and find out about related events (competitions, workshops, tutorials) running. Each competition hosted one or more scientific competitions over the duration of the ELSA project.
You can still register on the platform in order to get access to download materials and to submit your own methods to the competition.
ELSA Publications and Deliverables on Zenodo
ELSA contributes to the EU Open Research Repository on Zenodo, where you can find Research outputs from Horizon Europe, Euratom and earlier Framework Programs. There, you can access ELSA’s public deliverables as well as ELSA-acknowledging and acknowledged papers.
On Zenodo, search for “ELSA European Lighthouse on Secure and Safe AI”.
Webinars and Workshops
MLSec Seminars
ELSA has been supporting the MLSec Laboratory to present a series of seminars featuring presentations by some of the world’s leading researchers in the field of Machine Learning Security. The webinars have featured highly experienced researchers in the field presenting research and revelations on secure and safe machine learning.
You can find them seminars online: Discover past seminars and access the course materials.
Complementary short courses are available on YouTube: Watch short courses.
Workshop “AI in Cybersecurity: Offensive Capabilities, Impacts, and Response Strategies“
The workshop “AI in Cybersecurity: Offensive Capabilities, Impacts, and Response Strategies“ was part of the Final ELSA General Assembly in May 2026. Eight compelling talks from experts from all over Europe are available on the ELSA YouTube channel.
