Communication Efficient Secure and Private Multi-Party Deep Learning
Proceedings on Privacy Enhancing Technologies · 2025-01 · 2025 (1) · 169-183
DOI: 10.56553/popets-2025-0010 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings on Privacy Enhancing Technologies, 2025-01. Verfasst von Sankha Das und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Distributed training that enables multiple parties to jointly train a model on their respective datasets is a promising approach to address the challenges of large volumes of diverse data for training modern machine learning models. However, this approach immedi- ately raises security and privacy concerns; both about each party wishing to protect its data from other parties during training and preventing leakage of private information from the model after training through various inference attacks. In this paper, we ad- dress both these concerns simultaneously by designing efficient Differentially Private, secure Multiparty Computation (DP-MPC) protocols for jointly training a model on data distributed among multiple parties. Our DP-MPC protocol in the two-party setting is 56-794× more communication-efficient and 16-182× faster than previous such protocols. Conceptually, our work simplifies and improves on previous attempts to combine techniques from secure multiparty computation and differential privacy, especially in the context of ML training.
Zitieren
APA
Das, S., Chowdhury, S. R., Chandran, N., Gupta, D., Lokam, S., & Sharma, R. (2025). Communication Efficient Secure and Private Multi-Party Deep Learning. Proceedings on Privacy Enhancing Technologies, 2025(1), 169-183. https://doi.org/10.56553/popets-2025-0010
Vancouver
Das S, Chowdhury SR, Chandran N, Gupta D, Lokam S, Sharma R. Communication Efficient Secure and Private Multi-Party Deep Learning. Proceedings on Privacy Enhancing Technologies. 2025;2025(1):169-183. doi:10.56553/popets-2025-0010
BibTeX
@article{Das2025,
author = {Das, Sankha and Chowdhury, Sayak Ray and Chandran, Nishanth and Gupta, Divya and Lokam, Satya and Sharma, Rahul},
title = {Communication Efficient Secure and Private Multi-Party Deep Learning},
journal = {Proceedings on Privacy Enhancing Technologies},
year = {2025},
volume = {2025},
number = {1},
pages = {169--183},
doi = {10.56553/popets-2025-0010}
}
EUVIMED