Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6404-6412
DOI: 10.1609/aaai.v38i6.28460 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Lulu Xue und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only. However, gradient inversion attacks (GIAs), which recover users' training data from shared gradients, impose severe privacy threats to CL. Existing defense methods adopt different techniques, e.g., differential privacy, cryptography, and perturbation defenses, to defend against the GIAs. Nevertheless, all current defense methods suffer from a poor trade-off between privacy, utility, and efficiency. To mitigate the weaknesses of existing solutions, we propose a novel defense method, Dual Gradient Pruning (DGP), based on gradient pruning, which can improve communication efficiency while preserving the utility and privacy of CL. Specifically, DGP slightly changes gradient pruning with a stronger privacy guarantee. And DGP can also significantly improve communication efficiency with a theoretical analysis of its convergence and generalization. Our extensive experiments show that DGP can effectively defend against the most powerful GIAs and reduce the communication cost without sacrificing the model's utility.
Zitieren
APA
Xue, L., Hu, S., Zhao, R., Zhang, L. Y., Hu, S., Sun, L., & Yao, D. (2024). Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6404-6412. https://doi.org/10.1609/aaai.v38i6.28460
Vancouver
Xue L, Hu S, Zhao R, Zhang LY, Hu S, Sun L, et al. Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6404-6412. doi:10.1609/aaai.v38i6.28460
BibTeX
@article{Xue2024,
author = {Xue, Lulu and Hu, Shengshan and Zhao, Ruizhi and Zhang, Leo Yu and Hu, Shengqing and Sun, Lichao and Yao, Dezhong},
title = {Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {6404--6412},
doi = {10.1609/aaai.v38i6.28460}
}
EUVIMED