DEMOCRITUS UNIVERSITY OF THRACE

Algorithms.
Privacy.
Responsible AI.

Euclid is the Algorithms and Privacy Research Unit of the Programming and Data Processing Lab at Democritus University of Thrace.

OUR FOCUS

Responsible by design.

Privacy · Sustainability · Explainability

OUR RESEARCH

Foundations. New frontiers.

Exploring algorithmic challenges in contemporary and emerging domains of computer science.

Algorithms

Design, analysis and randomized methods.

Privacy

Algorithmic aspects of privacy and privacy-enhancing technologies.

Federated learning

Machine learning across distributed data sources.

Networks and opinion dynamics

Social networks, graphs and information diffusion.

Blockchain

Distributed ledgers and decentralized systems.

OUR MISSION

Advancing the science. Respecting the human.

The design and analysis of algorithms is fundamental to computer science. Euclid explores algorithmic challenges in contemporary and emerging domains, including social network analysis, privacy-enhancing technologies, federated machine learning and blockchain. Our mission is to advance responsible AI: privacy-enhanced, sustainable and explainable systems grounded in ethical and human-centered design.

PROJECTS

Our research in action

Research Project

Completed

SUSANNA

Jul 2023 — Nov 2023

SUSANNA project aims to redefine water meter management. The primary objective of this project is the establishment of a robust and secure blockchain network specifically designed for IoT water meter…

AWARDS

Research on a global stage

2023

NeurIPS 2023 – Machine Unlearning by Google

Winner - 6th Place

Google

https://www.kaggle.com/competitions/neurips-2023-machine-unlearning/writeups/algorithmic-amnesiacs-6th-place-solution-for-the-n

Members of the Euclid Team in collaboration with members of Archimedes Research Unit at Athena Research Center took part in the “NeurIPS 2023 - Machine Unlearning” competition held under the…

PUBLICATIONS

Ideas, methods & findings

Conference Proceeding

A Federated Explainable AI Model for Breast Cancer Classification

Eleni Briola, Christos Chrysanthos Nikolaidis, Vasileios Perifanis, Nikolaos Pavlidis, Pavlos Efraimidis

European Interdisciplinary Cybersecurity Conference, 2024

Breast cancer diagnosis is a crucial domain where Explainable Artificial Intelligence (XAI) integration holds immense importance. Understanding AI model decisions not only enhances trust but also aids in…

Journal Article

Advancing elderly social care dropout prediction with federated learning: client selection and imbalanced data management

Christos Chrysanthos Nikolaidis, Pavlos S. Efraimidis

Cluster Computing, 2024

Accurate prediction of user dropout is crucial for enhancing the effectiveness of social care applications developed for the elderly. Given the sensitive nature of healthcare data, this study…

Book Chapter

Carbon-Aware Machine Learning: A Case Study on Cellular Traffic Forecasting with Spiking Neural Networks

Theodoros Tsiolakis, Nikolaos Pavlidis, Vasileios Perifanis, Pavlos S. Efraimidis

IFIP Advances in Information and Communication Technology, 2024

RESEARCH & EDUCATION

Algorithms.
Privacy.
Responsible AI.

Foundations. New frontiers.

Algorithms

Privacy

Federated learning

Networks and opinion dynamics

Blockchain

Advancing the science. Respecting the human.

Our research in action

SUSANNA

Research on a global stage

NeurIPS 2023 – Machine Unlearning by Google

Ideas, methods & findings

A Federated Explainable AI Model for Breast Cancer Classification

Advancing elderly social care dropout prediction with federated learning: client selection and imbalanced data management

Carbon-Aware Machine Learning: A Case Study on Cellular Traffic Forecasting with Spiking Neural Networks

Explore. Learn. Collaborate.

Let’s advance research.

Algorithms.Privacy.Responsible AI.

Foundations. New frontiers.

Algorithms

Privacy

Federated learning

Networks and opinion dynamics

Blockchain

Advancing the science. Respecting the human.

Our research in action

SUSANNA

Research on a global stage

NeurIPS 2023 – Machine Unlearning by Google

Ideas, methods & findings

A Federated Explainable AI Model for Breast Cancer Classification

Advancing elderly social care dropout prediction with federated learning: client selection and imbalanced data management

Carbon-Aware Machine Learning: A Case Study on Cellular Traffic Forecasting with Spiking Neural Networks

Explore. Learn. Collaborate.

Algorithms.
Privacy.
Responsible AI.