30 October, 2019


Scientific publications

1.    G. Collinge, E. Lupu, L. Muñoz-González.  Defending against Poisoning Attacks in Online Learning Settings. Proceedings of the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. ESANN. April 2019. Bruges, Belgium. (Download)

2.   T. Timan, Z. Mann (Eds.), R. Araujo, A. Crespo-García, A. Farkash, A. Garnier, A. Vivian-Kiousi, P. Koster, A. Kung, G. Livraga, R. Díaz-Morales, M. Önen, A. Palomares, A. Navia-Vázquez, A. Metzger (contributors). Data protection in the era of artificial intelligence. Trends, existing solutions and recommendations for  privacy-preserving technologies, October 2019. BDVA position paper. (Download)

3.    Gusmeroli S., Dalle Carbonare D. (eds). Big Data challenges in Smart
Manufacturing Industry (ed. 2020). BDVA Whitepaper. (Download)

4.   A. Navia Vázquez, M.A. Vázquez-López and J. Cid-Sueiro. Double Confidential Federated Machine Learning Logistic Regression for Industrial Data Platforms. International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2020 (FL-ICML’20) July, 2020. (Download)

5. Perelló Nieto, Miquel & Santos-Rodriguez, Raul & García-García, Darío & Cid-Sueiro, Jesús. (2020). Recycling Weak Labels for Multiclass Classification. Neurocomputing. (Download)

6.    A. Navia-Vázquez, M.A. Vázquez,  and J. Cid-Sueiro. First vs Second Order Doubly Confidential Distributed Learning for Logistic Regression. IEEE Transactions on Parallel and Distributed Systems. Submitted Jan 2021. (Under review)

7.    G. Zizzo, A. Rawat, M. Sinn, B. Buesser. FAT: Federated Adversarial Training. NeurIPS 2020 Workshop on Scalability, Privacy, and Security in Federated Learning (SpicyFL) December 5th-12th, 2020 – Virtual Only.

8.   A. Navia-Vázquez, R. Díaz-Morales, M. Fernández-Díaz, Budget Distributed Support Vector Machine for Non-ID Federated Learning Scenarios. ACM Transactions on Intelligent Systems and Technology. Special Issue on Federated Learning: Algorithms, Systems, and Applications. Submitted March 2021. (Under review)

9.    S. Rossello, S., L. Muñoz-González, and R. Díaz Morales. Data protection by design in AI. The case of federated learning. Computerrecht: Tijdschrift voor Informatica, Telecommunicatie en Recht 3 (May 2021): 273-279. (Download)

10.    S. Bonura, D. Dalle Carbonare, R. Díaz-Morales, A. Navia-Vázquez, M. Purcell and S. Rossello. Increasing Trust within a Data Space with Federated learning, in Data Spaces: Design, Deployments, and Future Directions, BDVA Book Chapter. 2021. (Download)

11.    S. Bonura, D. Dalle Carbonare, R. Díaz-Morales, M. Fernández-Díaz, L. Morabito, L. Muñoz-González,  C. Napione, A. Navia-Vázquez, M. Purcell. Privacy Preserving Technologies for Trusted Data Spaces, BDVA Book Chapter. 2021. (Download)

12.    A. Rawat, G. Zizzo, M. Zaid Hameed, and L. Muñoz-González, Security and Robustness in Federated Machine Learning. Book chapter in “Federated Learning: A Comprehensive Overview of Methods and Applications”. Springer, 2021. (In press)

13.    A. Navia-Vázquez, M.A. Vázquez, and J. Cid-Sueiro. “A Priori” Shapley Data Value Estimation for Risk-Balanced Data Monetization in  Federated Learning. Journal of Neurocomputing, Elsevier. Submitted Nov. 2021. (Under review)

14.    Bottoni, Simone, Stefano Braghin, Theodora Brisimi, and Alberto Trombetta, Privacy-Preserving Distributed Support Vector Machines. In Heterogeneous Data Management, Polystores, and Analytics for Healthcare: VLDB Workshops, Poly 2021 and DMAH 2021, Virtual Event, August 20, 2021, Revised Selected Papers, pp. 85-102. 2021. (Download)

Conference presentations

1.    Conference Big Data and AI Tech World 2019, 12/03/2019. (Website)

2.    ECR 2019, European Society of Radiology. 28/02 -03/03/2019. Austria. (Website)

3.    AI Law & Ethics Conference, KU LEUVEN, 28/02/2019, Belgium. (Website)

4.   9th Annual Data Protection and Privacy Conference, 20/03/2019, Belgium. (Website)

5.    Towards Value Centric Big Data Workshop (E-Sides), 02/04/2019, Belgium. (Website)

6.     Spotlight on Ethics and Bias in AI for Healthcare. London Clinical and Health Data Science Meetup, 16/05/2019. (Website)

7.     Biotronics3D Workshop: welcome to the future of Radiology. 24/05/2019. (Website)

8.    Workshop on Artificial Intelligence for Manufacturing, EFFRA, BDVA, euRobotics, 02/07/2019. Belgium. (Website)

9.     Liaisons with National Initiatives. The London Medical Imaging & Artificial Intelligence Centre for Value Based Healthcare. 8/09/2019, UK. (Website)

10.     Delivering Data Protection in Real Time Workshop, Oxford University / OASIS, 09/09/2019, UK. (Website)

11.    Common European data spaces for Smart Manufacturing Conference, 16/09/2019, Belgium. (Website)

12.    Big Things 2019, 01/11/2019. (Website, YouTube)

13.     Digitalization of Knowledge and Industrial Technologies Conference. University of Bologna, 7/11/19, Italy. (Website)

14.    Theory and Practice of Differential Privacy (TPDP) at 26th ACM Conference on Computer and Communications Security (CCS 2019), 11/11/2019. (Website)

15.     Conference on Big Data LDN. London, UK, 13-14/11/2019. (Website)

16.    Liaisons with National Initiatives. The London Medical Imaging & Artificial Intelligence Centre for Value Based Healthcare. 21/11/2019, UK. (Website)

17.   Privacy in Machine Learning (PriML) at NeurIPS 2019, 14/12/2019, Canada. (Website)

18.    AI Law & Ethics Conference, 18/02/2020, Belgium. (Website)

19.     Conference for Participation on drafting of the Best Success Story for BDVA. BDVA Activity Group Conference, BDVA, 30/04/2020.

20.    Data protection impact assessment: the MUSKETEER’s project as a use-case. 12/10/2021. Workshop with data protection law experts of the KUL’s Center for IT and IP Law.

21.    Citip’s Safe-Deed closing event. Addressing legal, technical and ethical challenges in the data market context. 02/12/2021. (Website)

Dissemination material

MUSKETEER Project Brochure

Best Success Story Contest Data Economy meets Industry 4.0 to create the next generation of Smart Manufacturing thanks to Federated Learning – Full story

Best Success Story Federated Machine Learning to support Diagnostic Imaging for next generation AI-powered healthcare

Public deliverables

D2.1 Industrial and technical requirements

D2.3 Key performance indicators selection and definition

D2.7 Key performance indicators selection and definition – Final version

D3.1 Architecture Design – Initial Version

D3.2 Architecture Design – Final Version

D3.3 First prototype of the MUSKETEER platform

D3.4 Final prototype of the MUSKETEER platform

D4.1 Investigative overview of targeted architecture and algorithms

D4.2 Pre-processing, normalization, data alignment and data value estimation algorithms – Initial version

D4.3 Pre-processing, normalization, data alignment and data value estimation algorithms – Final version

D4.5 Machine learning algorithms over federated operation modes – Final version

D4.7 Machine Learning algorithms over semi honest operation modes – Final version

D5.1 Threat analysis for federated machine learning algorithms

D6.1 Assessment Framework design and specification

D6.2 Scalability of machine learning algorithms over every POMs

D6.3 Security of federated machine learning algorithms

D7.1 Client connectors’ architecture design

D7.2 Client connectors architecture design – Final version

D7.3 First prototype of the MUSKETEER client connectors

D7.4 Final prototype of the MUSKETEER client connectors

D7.5 Use case execution and KPI evaluation in the Smart Manufacturing domain

D7.6 Use case execution and KPI evaluation in the Health domain

D8.1 Project website and communication material

D8.2 Dissemination and communication plan

D8.3 Project communication and engagement activities

D8.4 Scientific dissemination activities

D8.5 Community engagement and technology transfer activities

D8.6 Evaluation and impact assessment