Menu responsive

Practical cryptographic schemes for analysing data in a privacy-preserving way.

Effectively combine cryptography with the principles of differential privacy

 

Besides processing statistical data in a privacy-preserving way, we also aim to enable a richer, more balanced and comprehensive approach where data analytics and cryptography go hand in hand to enable text, image and video processing.

Cryptography

Cryptographic protocol based on HHE to collect data from multiple sources and compute specific functions over them, in a privacy-preserving way.

Privacy

 Creating a digitally blind evaluation system.

AI

Federated learning and decentralized deep learning allow to process large information volume faster.

Big Data

Use large volumes of user data to adopt, improve and fine tune services.

In a Nutshell

Availability of Big Data combined with advancements in Artificial Intelligence (AI) enable broad capabilities for both private and public actors. However, cross-organisation and cross-border data sharing in-line with GDPR is increasingly difficult, as collection of granular, multi-dimensional personal data meets improved capabilities to cross-link data sets.

HARPOCRATES leverages novel cryptographic schemes to advance the capabilities of Privacy Preserving Machine Learning (PPML) and Federated Learning (FL), thus enabling decentralised training, validation, and prediction on encrypted data. Such privacy-preserving services and secure computation enable users to both benefit from cloud-based machine intelligence and maintain control over data.

HARPOCRATES will enable digitally blind evaluation systems demonstrated in practical application scenarios, helping build fairer, democratic, and unbiased societies.

Harpocrates team comprises a consortium of 13 members, including universities, university hospitals, SMEs and regional government administration bodies.

Different countries including United Kingdom, Finland, Sweden, Ireland, Serbia, Germany, Spain, Italy and France.

Coordinator of the project is Tampere University, Finland. Project kickoff is in October and its planned to last until October 2025.

Harpocrates project is financed by EU Commission with the total budget of 4 mil EU and £0.34 mil by UKRI.

Our latest news to stay in focus of how we do it

News

Building Trust in AI: Highlights from the European AI & Cybersecurity CrossTalk Event

The recent European AI & Cybersecurity Network CrossTalk event in Brussels brought together several projects dedicated to addressing key challenges in data security and AI privacy. Held at the Emilia-Romagna Delegation to the EU, the event covered a range of practical topics…

News

Press release: European AI Security network CrossTalk event: leading the future of AI in Healthcare

News

European AI & Cybersecurity Network Crosstalk on Project Solutions

Our Partners

 

Subscribe To Our Newsletter

Enter your email to get notified with the latest news and events