FREDY: Federated Resilience Enhanced with Differential Privacy

Zacharias Anastasakis (), Terpsichori-Helen Velivassaki, Artemis Voulkidis, Stavroula Bourou, Konstantinos Psychogyios, Dimitrios Skias and Theodore Zahariadis ()
Additional contact information
Zacharias Anastasakis: Synelixis Solutions S.A., GR34100 Chalkida, Greece
Terpsichori-Helen Velivassaki: Synelixis Solutions S.A., GR34100 Chalkida, Greece
Artemis Voulkidis: Synelixis Solutions S.A., GR34100 Chalkida, Greece
Stavroula Bourou: Synelixis Solutions S.A., GR34100 Chalkida, Greece
Konstantinos Psychogyios: Synelixis Solutions S.A., GR34100 Chalkida, Greece
Dimitrios Skias: Netcompany-Intrasoft S.A., GR19002 Paiania, Greece
Theodore Zahariadis: Rural Development, Agrifood, and Natural Resources Management, University of Athens, GR15772 Athens, Greece

Future Internet, 2023, vol. 15, issue 9, 1-16

Abstract: Federated Learning is identified as a reliable technique for distributed training of ML models. Specifically, a set of dispersed nodes may collaborate through a federation in producing a jointly trained ML model without disclosing their data to each other. Each node performs local model training and then shares its trained model weights with a server node, usually called Aggregator in federated learning, as it aggregates the trained weights and then sends them back to its clients for another round of local training. Despite the data protection and security that FL provides to each client, there are still well-studied attacks such as membership inference attacks that can detect potential vulnerabilities of the FL system and thus expose sensitive data. In this paper, in order to prevent this kind of attack and address private data leakage, we introduce FREDY, a differential private federated learning framework that enables knowledge transfer from private data. Particularly, our approach has a teachers–student scheme. Each teacher model is trained on sensitive, disjoint data in a federated manner, and the student model is trained on the most voted predictions of the teachers on public unlabeled data which are noisy aggregated in order to guarantee the privacy of each teacher’s sensitive data. Only the student model is publicly accessible as the teacher models contain sensitive information. We show that our proposed approach guarantees the privacy of sensitive data against model inference attacks while it combines the federated learning settings for the model training procedures.

Keywords: differential privacy; privacy preserving; federated learning; cyber security; knowledge transfer; noisy aggregation (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/15/9/296/pdf (application/pdf)
https://www.mdpi.com/1999-5903/15/9/296/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:15:y:2023:i:9:p:296-:d:1230890

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().