Can Contributing More Put You at a Higher Leakage Risk? The Relationship Between Shapley Value and Training Data Leakage Risks in Federated Learning

Soumia Zohra El Mestari, Maciej Krzysztof Zuziak, Gabriele Lenzini, Salvatore Rinzivillo

2025

Abstract

Federated Learning (FL) is a crucial approach for training large-scale AI models while preserving data locality, eliminating the need for centralised data storage. In collaborative learning settings, ensuring data quality is essential, and in FL, maintaining privacy requires limiting the knowledge accessible to the central orchestrator, which evaluates and manages client contributions. Accurately measuring and regulating the marginal impact of each client’s contribution needs specialised techniques. This work examines the relationship between one such technique—Shapley Values—and a client’s vulnerability to Membership inference attacks (MIAs). Such a correlation would suggest that the contribution index could reveal high-risk participants, potentially allowing a malicious orchestrator to identify and exploit the most vulnerable clients. Conversely, if no such relationship is found, it would indicate that contribution metrics do not inherently expose information exploitable for powerful privacy attacks. Our empirical analysis in a cross-silo FL setting demonstrates that leveraging contribution metrics in federated environments does not substantially amplify privacy risks.

Paper Citation

in Harvard Style

El Mestari S., Zuziak M., Lenzini G. and Rinzivillo S. (2025). Can Contributing More Put You at a Higher Leakage Risk? The Relationship Between Shapley Value and Training Data Leakage Risks in Federated Learning. In Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-760-3, SciTePress, pages 275-286. DOI: 10.5220/0013639000003979

in Bibtex Style

@conference{secrypt25,
author={Soumia El Mestari and Maciej Zuziak and Gabriele Lenzini and Salvatore Rinzivillo},
title={Can Contributing More Put You at a Higher Leakage Risk? The Relationship Between Shapley Value and Training Data Leakage Risks in Federated Learning},
booktitle={Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2025},
pages={275-286},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013639000003979},
isbn={978-989-758-760-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 22nd International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - Can Contributing More Put You at a Higher Leakage Risk? The Relationship Between Shapley Value and Training Data Leakage Risks in Federated Learning
SN - 978-989-758-760-3
AU - El Mestari S.
AU - Zuziak M.
AU - Lenzini G.
AU - Rinzivillo S.
PY - 2025
SP - 275
EP - 286
DO - 10.5220/0013639000003979
PB - SciTePress