English
Related papers

Related papers: Differential Privacy Guarantees for Stochastic Gra…

200 papers

Recently, due to the popularity of deep neural networks and other methods whose training typically relies on the optimization of an objective function, and due to concerns for data privacy, there is a lot of interest in differentially…

Machine Learning · Computer Science 2025-02-12 Antoine Barczewski , Jan Ramon

Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning. While many TD learning methods have been developed in recent years, little attention has been paid to preserving privacy and most of…

Machine Learning · Computer Science 2022-01-26 Canzhe Zhao , Yanjie Ze , Jing Dong , Baoxiang Wang , Shuai Li

The vanilla Differentially-Private Stochastic Gradient Descent (DP-SGD), including DP-Adam and other variants, ensures the privacy of training data by uniformly distributing privacy costs across training steps. The equivalent privacy costs…

Machine Learning · Computer Science 2022-01-19 Jian Du , Song Li , Xiangyi Chen , Siheng Chen , Mingyi Hong

Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning framework, which…

Machine Learning · Computer Science 2022-10-20 Junyuan Hong , Zhangyang Wang , Jiayu Zhou

In this paper, we consider efficient differentially private empirical risk minimization from the viewpoint of optimization algorithms. For strongly convex and smooth objectives, we prove that gradient descent with output perturbation not…

Machine Learning · Computer Science 2017-05-25 Jiaqi Zhang , Kai Zheng , Wenlong Mou , Liwei Wang

Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy.…

Machine Learning · Computer Science 2019-10-29 Eugene Bagdasaryan , Vitaly Shmatikov

Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient updates. However, conventional mechanisms such as Gaussian…

Cryptography and Security · Computer Science 2025-09-09 Qin Yang , Nicholas Stout , Meisam Mohammady , Han Wang , Ayesha Samreen , Christopher J Quinn , Yan Yan , Ashish Kundu , Yuan Hong

Differential Privacy (DP) mechanisms, especially in high-dimensional settings, often face the challenge of maintaining privacy without compromising the data utility. This work introduces an innovative shuffling mechanism in…

Machine Learning · Computer Science 2024-07-23 Jungang Yang , Zhe Ji , Liyao Xiang

Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…

Machine Learning · Computer Science 2023-05-25 Geon Heo , Junseok Seo , Steven Euijong Whang

Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include sensitive information, such as personal contact details,…

Machine Learning · Statistics 2026-02-10 Zhongjie Shi , Puyu Wang , Chenyang Zhang , Yuan Cao

In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private. Compared to the classical gradient descent algorithm where updates operate on a single model vector and controlled noise…

Machine Learning · Computer Science 2021-03-16 Georgios Damaskinos , Celestine Mendler-Dünner , Rachid Guerraoui , Nikolaos Papandreou , Thomas Parnell

Machine learning (ML) models trained by differentially private stochastic gradient descent (DP-SGD) have much lower utility than the non-private ones. To mitigate this degradation, we propose a DP Laplacian smoothing SGD (DP-LSSGD) to train…

Machine Learning · Computer Science 2019-12-10 Bao Wang , Quanquan Gu , March Boedihardjo , Farzin Barekat , Stanley J. Osher

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…

Information Theory · Computer Science 2020-01-17 Shahab Asoodeh , Jiachun Liao , Flavio P. Calmon , Oliver Kosut , Lalitha Sankar

We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearning (Chien et al., 2024), obtaining a better…

Differentially private stochastic gradient descent (DP-SGD) has been widely adopted in deep learning to provide rigorously defined privacy, which requires gradient clipping to bound the maximum norm of individual gradients and additive…

Machine Learning · Computer Science 2023-06-29 Junyi Zhu , Matthew B. Blaschko

Gradient leakage attacks are considered one of the wickedest privacy threats in deep learning as attackers covertly spy gradient updates during iterative training without compromising model training quality, and yet secretly reconstruct…

Machine Learning · Computer Science 2021-12-28 Wenqi Wei , Ling Liu

Introducing noise in the training of machine learning systems is a powerful way to protect individual privacy via differential privacy guarantees, but comes at a cost to utility. This work looks at whether the inherent randomness of…

Machine Learning · Computer Science 2022-03-01 Stephanie L. Hyland , Shruti Tople

Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…

Machine Learning · Computer Science 2021-10-14 Friedrich Dörmann , Osvald Frisk , Lars Nørvang Andersen , Christian Fischer Pedersen

The hidden state threat model of differential privacy (DP) assumes that the adversary has access only to the final trained machine learning (ML) model, without seeing intermediate states during training. However, the current privacy…

Machine Learning · Computer Science 2025-05-27 Rob Romijnders , Antti Koskela

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

Machine Learning · Statistics 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence