paper-with-me

Papers

Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning

2021-02-25 · ICLR 2021 1 · Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu

The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism. However, for meaningful privacy parameters, a differentially private model degrades the utility drastically when the model comprises a large number of trainable parameters. In this paper, we propose an algorithm \emph{Gradient Embedding Perturbation (GEP)} towards training differentially private deep models with decent accuracy. Specifically, in each gradient descent step, GEP first projects individual private gradient into a non-sensitive anchor subspace, producing a low-dimensional gradient embedding and a small-norm residual gradient. Then, GEP perturbs the low-dimensional embedding and the residual gradient separately according to the privacy budget. Such a decomposition permits a small perturbation variance, which greatly helps to break the dimensional barrier of private learning. With GEP, we achieve decent accuracy with reasonable computational cost and modest privacy guarantee for deep models. Especially, with privacy bound $\epsilon=8$, we achieve $74.9\%$ test accuracy on CIFAR10 and $95.1\%$ test accuracy on SVHN, significantly improving over existing results.

📄 PDF Abstract BibTeX arXiv:2102.12677

Code (2)

dayu11/Differentially-Private-Deep-Learning 공식 구현 pytorch
dayu11/Gradient-Embedding-Perturbation 공식 구현 pytorch

Similar Papers 제목 키워드 기반

DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning

2021-12-24 · Ismat Jarin, Birhanu Eshete

Differential Privacy (DP) has emerged as a rigorous formalism to reason about quantifiable privacy leakage. In machine learning (ML), DP has been employed to limit inference/disclosure of training examples. Prior work le…

BIG-bench Machine LearningInference AttackMembership Inference Attackregression

Gradient Perturbation is Underrated for Differentially Private Convex Optimization

2019-11-26 · Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu 외

Gradient perturbation, widely used for differentially private optimization, injects noise at every iterative update to guarantee differential privacy. Previous work first determines the noise level that can satisfy the p…

Adversarial Signed Graph Learning with Differential Privacy

2025-11-29 · Haobin Ke, Sen Zhang, Qingqing Ye, Xun Ran 외 arxiv

Signed graphs with positive and negative edges can model complex relationships in social networks. Leveraging on balance theory that deduces edge signs from multi-hop node pairs, signed graph learning can generate node e…

Graph Learning

Large-Scale Privacy-Preserving Network Embedding against Private Link Inference Attacks

2022-05-28 · Xiao Han, Leye Wang, Junjie Wu, Yuncong Yang

Network embedding represents network nodes by a low-dimensional informative vector. While it is generally effective for various downstream tasks, it may leak some private information of networks, such as hidden private l…

Network EmbeddingPrivacy Preserving

A Differentially Private Framework for Deep Learning with Convexified Loss Functions

2022-04-03 · Zhigang Lu, Hassan Jameel Asghar, Mohamed Ali Kaafar, Darren Webb 외

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and out…

Sensitivity