Related papers: A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via $f$-Divergences

A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via $f$-Divergences

URL: http://arxiv.org/abs/2001.05990v1
Date: Thu, 16 Jan 2020 18:45:05 GMT
Title: A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via $f$-Divergences
Authors: Shahab Asoodeh, Jiachun Liao, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar
Abstract summary: Our result is based on the joint range of two $f-divergences that underlie the approximate and the R'enyi variations of differential privacy. When compared to the state-of-the-art, our bounds may lead to about 100 more gradient descent iterations for training deep learning models for the same privacy budget.
Score: 14.008231249756678
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R\'enyi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie the approximate and the R\'enyi variations of differential privacy. We apply our result to the moments accountant framework for characterizing privacy guarantees of stochastic gradient descent. When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget.

Related papers

Private Fine-tuning of Large Language Models with Zeroth-order Optimization [54.24600476755372]
We introduce DP-ZO, a new method for fine-tuning large language models that preserves the privacy of training data by privatizing zeroth-order optimization. We show that DP-ZO exhibits just $1.86%$ performance degradation due to privacy at $ (1,10-5)$-DP when fine-tuning OPT-66B on 1000 training samples from SQuAD.
arXiv Detail & Related papers (2024-01-09T03:53:59Z)
Sparsity-Preserving Differentially Private Training of Large Embedding Models [67.29926605156788]
DP-SGD is a training algorithm that combines differential privacy with gradient descent. Applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. We present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
arXiv Detail & Related papers (2023-11-14T17:59:51Z)
SA-DPSGD: Differentially Private Stochastic Gradient Descent based on Simulated Annealing [25.25065807901922]
Differentially private gradient descent is the most popular training method with differential privacy in image recognition. Existing DPSGD schemes lead to significant performance degradation, which prevents the application of differential privacy. We propose a simulated annealing-based differentially private gradient descent scheme (SA-DPSGD) which accepts a candidate update with a probability that depends on the update quality and on the number of iterations.
arXiv Detail & Related papers (2022-11-14T09:20:48Z)
Directional Privacy for Deep Learning [2.826489388853448]
Differentially Private Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. Metric DP, however, can provide alternative mechanisms based on arbitrary metrics that might be more suitable for preserving utility. We show that this provides both $epsilon$-DP and $epsilon d$-privacy for deep learning training, rather than the $(epsilon, delta)$-privacy of the Gaussian mechanism.
arXiv Detail & Related papers (2022-11-09T05:18:08Z)
Differentially Private Stochastic Gradient Descent with Low-Noise [49.981789906200035]
Modern machine learning algorithms aim to extract fine-grained information from data to provide accurate predictions, which often conflicts with the goal of privacy protection. This paper addresses the practical and theoretical importance of developing privacy-preserving machine learning algorithms that ensure good performance while preserving privacy.
arXiv Detail & Related papers (2022-09-09T08:54:13Z)
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent [69.14164921515949]
We characterize privacy guarantees for individual examples when releasing models trained by DP-SGD. We find that most examples enjoy stronger privacy guarantees than the worst-case bound. This implies groups that are underserved in terms of model utility simultaneously experience weaker privacy guarantees.
arXiv Detail & Related papers (2022-06-06T13:49:37Z)
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning [74.73901662374921]
A differentially private model degrades the utility drastically when the model comprises a large number of trainable parameters. We propose an algorithm emphGradient Embedding Perturbation (GEP) towards training differentially private deep models with decent accuracy.
arXiv Detail & Related papers (2021-02-25T04:29:58Z)
Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
arXiv Detail & Related papers (2020-09-18T20:18:35Z)
Three Variants of Differential Privacy: Lossless Conversion and Applications [13.057076084452016]
We consider three different variants of differential privacy (DP), namely approximate DP, R'enyi RDP, and hypothesis test. In the first part, we develop a machinery for relating approximate DP to iterations based on the joint range of two $f$-divergences. As an application, we apply our result to the moments framework for characterizing privacy guarantees of noisy gradient descent.
arXiv Detail & Related papers (2020-08-14T18:23:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.