中文
相关论文

相关论文: Private and Fair Machine Learning: Revisiting the …

200 篇论文

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.…

机器学习 · 计算机科学 2019-10-29 Eugene Bagdasaryan , Vitaly Shmatikov

As machine learning becomes more widespread throughout society, aspects including data privacy and fairness must be carefully considered, and are crucial for deployment in highly regulated industries. Unfortunately, the application of…

机器学习 · 计算机科学 2023-02-24 Maria S. Esipova , Atiyeh Ashari Ghomi , Yaqiao Luo , Jesse C. Cresswell

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…

机器学习 · 计算机科学 2022-10-06 Yannis Cattan , Christopher A. Choquette-Choo , Nicolas Papernot , Abhradeep Thakurta

Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, it was recently…

机器学习 · 计算机科学 2022-09-09 Cuong Tran , My H. Dinh , Ferdinando Fioretto

Recent works have shown that selecting an optimal model architecture suited to the differential privacy setting is necessary to achieve the best possible utility for a given privacy budget using differentially private stochastic gradient…

机器学习 · 计算机科学 2024-11-01 Anderson Santana de Oliveira , Caelin Kaplan , Khawla Mallat , Tanmay Chakraborty

Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the…

机器学习 · 计算机科学 2025-03-04 Zhiqi Bu , Ruixuan Liu

The worldwide adoption of machine learning (ML) and deep learning models, particularly in critical sectors, such as healthcare and finance, presents substantial challenges in maintaining individual privacy and fairness. These two elements…

机器学习 · 计算机科学 2024-04-16 Mengmeng Yang , Ming Ding , Youyang Qu , Wei Ni , David Smith , Thierry Rakotoarivelo

Differential privacy is a widely accepted measure of privacy in the context of deep learning algorithms, and achieving it relies on a noisy training approach known as differentially private stochastic gradient descent (DP-SGD). DP-SGD…

机器学习 · 计算机科学 2023-07-26 Ce Feng , Nuo Xu , Wujie Wen , Parv Venkitasubramaniam , Caiwen Ding

An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…

密码学与安全 · 计算机科学 2021-05-18 Franziska Boenisch , Philip Sperl , Konstantin Böttinger

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 classes and…

机器学习 · 计算机科学 2020-09-29 Depeng Xu , Wei Du , Xintao Wu

Deployment of deep learning in different fields and industries is growing day by day due to its performance, which relies on the availability of data and compute. Data is often crowd-sourced and contains sensitive information about its…

机器学习 · 计算机科学 2020-10-06 Tom Farrand , Fatemehsadat Mireshghallah , Sahib Singh , Andrew Trask

Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on different sub-groups in the population, which leads to a…

Training machine learning models with differential privacy (DP) has received increasing interest in recent years. One of the most popular algorithms for training differentially private models is differentially private stochastic gradient…

机器学习 · 计算机科学 2024-02-21 Ziteng Sun , Ananda Theertha Suresh , Aditya Krishna Menon

While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge,…

机器学习 · 统计学 2024-01-02 Tim Dockhorn , Tianshi Cao , Arash Vahdat , Karsten Kreis

In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versatility, DP-SGD…

机器学习 · 计算机科学 2024-01-02 Rachel Redberg , Antti Koskela , Yu-Xiang Wang

Privacy-preserving machine learning aims to train models on private data without leaking sensitive information. Differential privacy (DP) is considered the gold standard framework for privacy-preserving training, as it provides formal…

Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce fairness issues like disparate impact, and reduce adversarial robustness.…

机器学习 · 计算机科学 2026-04-21 Ruichen Xu , Kexin Chen

Differential privacy (DP) provides a formal privacy guarantee that prevents adversaries with access to machine learning models from extracting information about individual training points. Differentially private stochastic gradient descent…

密码学与安全 · 计算机科学 2022-12-15 Jie Fu , Zhili Chen , XinPeng Ling

In this paper, an adjustment to the original differentially private stochastic gradient descent (DPSGD) algorithm for deep learning models is proposed. As a matter of motivation, to date, almost no state-of-the-art machine learning…

机器学习 · 计算机科学 2021-07-13 Mehdi Amian

Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks,…

机器学习 · 计算机科学 2023-11-30 Jie Fu , Qingqing Ye , Haibo Hu , Zhili Chen , Lulu Wang , Kuncan Wang , Xun Ran
‹ 上一页 1 2 3 10 下一页 ›