CyberDFL

The main objective of the CyberDFL project is to research, design, and implement a framework that provides a range of measures to train and evaluate trustworthy and secure federated learning models in a decentralized manner. The framework will focus on strengthening critical pillars of Decentralized Federated Learning (DFL), such as robustness, privacy, reputation, and trustworthiness, ensuring resiliency against cyber threats. To achieve this goal, the following objectives are defined.

• Propose innovative attack approaches, including new types of poisoning attacks and novel topology inference attacks, which have yet to be explored in prior literature.
• Introduce novel defense mechanisms that leverage advanced, adaptive techniques to protect DFL privacy, especially in real-world, complex environments.
• Create new reputation mechanisms to ensure the trustworthiness of DFL model in adaptive federations

Pre-prints

• Chao Feng, Alberto Huertas Celdran, Xi Cheng, Gérôme Bovet, Burkhard Stiller: GreenDFL: a Framework for Assessing the Sustainability of Decentralized Federated Learning Systems; arxiv, arxiv, Zürich, Switzerland, February 2025, URL
• Chao Feng, Yuanzhe Gao, Alberto Huertas Celdran, Gerome Bovet, Burkhard Stiller: From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning;  arxiv, Zürich, Switzerland, January 2025, URL
• Chao Feng, Nicolas Fazli Kohler, Alberto Huertas Celdran, Gerome  Bovet, Burkhard Stiller:  ColNet: Collaborative Optimization in Decentralized Federated Multi-task  Learning Systems ;  arxiv, Zürich, Switzerland, January 2025, URL
• Pedro Miguel Sánchez Sánchez, Enrique Tomás Martínez Beltrán, Chao Feng, Gérôme Bovet, Gregorio Martínez Pérez, Alberto Huertas Celdrán: S-VOTE: Similarity-based Voting for Client Selection in Decentralized Federated Learning; arxiv, Zürich, Switzerland, January 2025, URL

Accepted Papers

• [Short Paper] Alberto Huertas Celdran, Chao Feng, Sabyasachi Banik, Gerome Bovet, Gregorio Martinez Perez, Burkhard Stiller: De-VertiFL: A Solution for Decentralized Vertical Federated Learning; 38th IEEE/IFIP Network Operations and Management Symposium (NOMS 2025), Honolulu, HI, USA, May 2025

Published Papers

• [Full Paper] Chao Feng, Alberto Huertas Celdran, Pedro Miguel Sanchez Sanchez, Jan Kreischer, Jan von der Assen, Gerome Bovet, Gregorio Martinez Perez, Burkhard Stiller: CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation; IEEE, IEEE Transactions on Dependable and Secure Computing, 2025, pp 1–14. URL

• University of Zurich, IFI, CSG
• Armasuisse
• University of Murcia 

• Prof. Dr. Burkhard Stiller
• Dr. Alberto Huertas Celdrán
• Jan von der Assen
• Chao Feng

Inquiries may be directed to the local Swiss project management:

Prof. Dr. Burkhard Stiller,

Dr. Alberto Huertas Celdrán
University of Zürich, IFI
Binzmühlestrasse 14
CH-8050 Zürich
Switzerland

stiller@ifi.uzh.ch,
huertas@ifi.uzh.ch
Phone: +41 44 635 75 85
Fax: +41 44 635 68 09