Horizon Europe: European Lighthouse on Secure and Safe AI – ELSA - Research Portal

Horizon Europe: European Lighthouse on Secure and Safe AI – ELSA

Project: Research

Description

ELSA is a virtual centre of excellence that will spearhead efforts in foundational safe and secure artificial intelligence (AI) methodology research. ELSA is a large and growing network of top European experts in AI and machine learning who aim to promote the development and deployment of cutting-edge AI solutions in the future and make Europe the world's lighthouse of AI.

ELSA brings together researchers from 26 top research institutions and companies in Europe to pool their expertise in the field of AI and machine learning. ELSA is coordinated by the CISPA Helmholtz Center for Information Security in Saarbrücken.

The ELSA project will be focusing on the following research programmes:

Technical robustness and security;
Privacy protection techniques and infrastructures; and
Human agency and oversight.
For more information regarding the ELSA project please go to the following link.

ELSA is funded by Horizon Europe, one of the largest research and innovation funding programmes in the world.

ELSA is built on the ELLIS Society (European Laboratory for Learning and Intelligent Systems) and works in close collaboration with ELISE (European Network of AI Excellence Centers).

Status	Active
Effective start/end date	1/09/22 → 31/08/25
Links	https://www.lancaster.ac.uk/scc/research/elsa/

Funding

UKRI: £428,540.00

Angelov, Plamen (Principal Investigator)

Research outputs

Multilayer Evolving Fuzzy Neural Networks
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Interpretable-Through-Prototypes Deepfake Detection for Diffusion Models
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Marine Debris Detection in Satellite Surveillance using Attention Mechanisms
Research output: Contribution to Journal/Magazine › Journal article › peer-review
PUDD: Towards Robust Multi-modal Prototype-based Deepfake Detection
Research output: Contribution to conference - Without ISBN/ISSN › Conference paper › peer-review
Self-Supervised Representation Learning for Adversarial Attack Detection
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Vision-based Landing Guidance through Tracking and Orientation Estimation
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
IDEAL: Interpretable-by-Design ALgorithms for learning from foundation feature spaces
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Explainable Audio-Visual Representation Learning via Prototypical Contrastive Masked Autoencoder
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Robust Self-Supervised Learning for Adversarial Attack Detection
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Detecting Cross-domain Deepfake Videos with Contrastive Prototype Learning
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Research