paper-with-me

Papers

Backpropagation Clipping for Deep Learning with Differential Privacy

2022-02-10 · Timothy Stevens, Ivoline C. Ngong, David Darais, Calvin Hirsch, David Slater, Joseph P. Near

We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning. Our approach clips each trainable layer's inputs (during the forward pass) and its upstream gradients (during the backward pass) to ensure bounded global sensitivity for the layer's gradient; this combination replaces the gradient clipping step in existing DP-SGD variants. Our approach is simple to implement in existing deep learning frameworks. The results of our empirical evaluation demonstrate that backpropagation clipping provides higher accuracy at lower values for the privacy parameter $\epsilon$ compared to previous work. We achieve 98.7% accuracy for MNIST with $\epsilon = 0.07$ and 74% accuracy for CIFAR-10 with $\epsilon = 3.64$.

📄 PDF Abstract BibTeX arXiv:2202.05089

Code (1)

uvm-plaid/backpropagation-clipping 공식 구현 pytorch

Tasks

Deep LearningPrivacy PreservingPrivacy Preserving Deep LearningSensitivity

Methods 이 논문이 사용한 방법론

Gradient Clipping One difficulty that arises with optimization of deep neural networks is that large parameter gradients can lead an SGD optimizer to update…

Similar Papers 제목 키워드 기반

An Adaptive Differentially Private Federated Learning Framework

2026-02-06 · Jin Wang, Hui Ma, Yajun Zhang, Xinjun Pei 외 arxiv

Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity and non-independent and identically distributed (N…

Dimensionality ReductionFederated Learning

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

2022-12-03 · Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang 외

Differentially private deep learning has recently witnessed advances in computational efficiency and privacy-utility trade-off. We explore whether further improvements along the two axes are possible and provide affirmat…

Computational Efficiency

Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy

2020-03-08 · Depeng Xu, Wei Du, Xintao Wu

When we enforce differential privacy in machine learning, the utility-privacy trade-off is different w.r.t. each group. Gradient clipping and random noise addition disproportionately affect underrepresented and complex c…

Multi-Objective Optimization for Privacy-Utility Balance in Differentially Private Federated Learning

2025-03-27 · Kanishka Ranaweera, David Smith, Pubudu N. Pathirana, Ming Ding 외

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning. However, ensuring differential pri…

Federated LearningPrivacy Preserving

Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy

2021-06-25 · Xinwei Zhang, Xiangyi Chen, Mingyi Hong, Zhiwei Steven Wu 외

Providing privacy protection has been one of the primary motivations of Federated Learning (FL). Recently, there has been a line of work on incorporating the formal privacy notion of differential privacy with FL. To guar…

Federated Learning