Loading…

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks

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 sever...

Full description

Saved in:
Bibliographic Details
Main Authors: Xue, Lulu, Hu, Shengshan, Zhao, Ruizhi, Zhang, Leo Yu, Hu, Shengqing, Sun, Lichao, Yao, Dezhong
Format: Conference Proceeding
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2159-5399
2374-3468
DOI:10.1609/aaai.v38i6.28460