中文
相关论文

相关论文: Scalable and Provably Accurate Algorithms for Diff…

200 篇论文

User-level privacy is important in distributed systems. Previous research primarily focuses on the central model, while the local models have received much less attention. Under the central model, user-level DP is strictly stronger than the…

机器学习 · 统计学 2024-05-28 Puning Zhao , Li Shen , Rongfei Fan , Qingming Li , Huiwen Wu , Jiafei Wu , Zhe Liu

We study the design of differentially private algorithms for adaptive analysis of dynamically growing databases, where a database accumulates new data entries while the analysis is ongoing. We provide a collection of tools for machine…

数据结构与算法 · 计算机科学 2018-03-20 Rachel Cummings , Sara Krehbiel , Kevin A. Lai , Uthaipon Tantipongpipat

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

Differential privacy is the state-of-the-art formal definition for data release under strong privacy guarantees. A variety of mechanisms have been proposed in the literature for releasing the output of numeric queries (e.g., the Laplace…

密码学与安全 · 计算机科学 2022-04-15 Victor A. E. Farias , Felipe T. Brito , Cheryl Flynn , Javam C. Machado , Subhabrata Majumdar , Divesh Srivastava

The application of differential privacy to the training of deep neural networks holds the promise of allowing large-scale (decentralized) use of sensitive data while providing rigorous privacy guarantees to the individual. The predominant…

This paper considers a distributed multi-agent optimization problem, with the global objective consisting of the sum of local objective functions of the agents. The agents solve the optimization problem using local computation and…

分布式、并行与集群计算 · 计算机科学 2017-11-07 Shripad Gade , Nitin H. Vaidya

How can agents exchange information to learn while protecting privacy? Healthcare centers collaborating on clinical trials must balance knowledge sharing with safeguarding sensitive patient data. We address this challenge by using…

机器学习 · 计算机科学 2025-03-19 Marios Papachristou , M. Amin Rahimian

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

机器学习 · 计算机科学 2023-05-31 Stephan Rabanser , Anvith Thudi , Abhradeep Thakurta , Krishnamurthy Dvijotham , Nicolas Papernot

Differential privacy (DP) provides robust privacy guarantees for statistical inference, but this can lead to unreliable results and biases in downstream applications. While several noise-aware approaches have been proposed which integrate…

机器学习 · 统计学 2026-05-29 Talal Alrawajfeh , Joonas Jälkö , Antti Honkela

Differential privacy is a promising privacy-preserving paradigm for statistical query processing over sensitive data. It works by injecting random noise into each query result, such that it is provably hard for the adversary to infer the…

数据库 · 计算机科学 2012-12-12 Ganzhao Yuan , Zhenjie Zhang , Marianne Winslett , Xiaokui Xiao , Yin Yang , Zhifeng Hao

Vertical Federated Learning (FL) is a new paradigm that enables users with non-overlapping attributes of the same data samples to jointly train a model without directly sharing the raw data. Nevertheless, recent works show that it's still…

机器学习 · 计算机科学 2022-10-05 Xiaochen Li , Yuke Hu , Weiran Liu , Hanwen Feng , Li Peng , Yuan Hong , Kui Ren , Zhan Qin

Decentralized min-max optimization allows multi-agent systems to collaboratively solve global min-max optimization problems by facilitating the exchange of model updates among neighboring agents, eliminating the need for a central server.…

机器学习 · 计算机科学 2025-08-12 Yueyang Quan , Chang Wang , Shengjie Zhai , Minghong Fang , Zhuqing Liu

Distributed aggregative optimization underpins many cooperative optimization and multi-agent control systems, where each agent's objective function depends both on its local optimization variable and an aggregate of all agents' optimization…

系统与控制 · 电气工程与系统科学 2026-03-30 Ziqin Chen , Yongqiang Wang

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…

机器学习 · 统计学 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

The training of neural networks with Differentially Private Stochastic Gradient Descent offers formal Differential Privacy guarantees but introduces accuracy trade-offs. In this work, we propose to alleviate these trade-offs in residual…

机器学习 · 计算机科学 2022-05-09 Helena Klause , Alexander Ziller , Daniel Rueckert , Kerstin Hammernik , Georgios Kaissis

Deep learning models leak significant amounts of information about their training datasets. Previous work has investigated training models with differential privacy (DP) guarantees through adding DP noise to the gradients. However, such…

机器学习 · 计算机科学 2020-07-23 Milad Nasr , Reza Shokri , Amir houmansadr

Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-tailed noise, which is common in training large language models.…

机器学习 · 计算机科学 2025-09-30 Saleh Vatan Khah , Savelii Chezhegov , Shahrokh Farahmand , Samuel Horváth , Eduard Gorbunov

We introduce a refined differentially private (DP) data structure for kernel density estimation (KDE), offering not only improved privacy-utility tradeoff but also better efficiency over prior results. Specifically, we study the…

数据结构与算法 · 计算机科学 2025-03-25 Erzhi Liu , Jerry Yao-Chieh Hu , Alex Reneau , Zhao Song , Han Liu

In machine learning, boosting is one of the most popular methods that designed to combine multiple base learners to a superior one. The well-known Boosted Decision Tree classifier, has been widely adopted in many areas. In the big data era,…

密码学与安全 · 计算机科学 2020-02-07 Sen Wang , J. Morris Chang

Differential privacy is one of the methods to solve the problem of privacy protection in federated learning. Setting the same privacy budget for each round will result in reduced accuracy in training. The existing methods of the adjustment…

密码学与安全 · 计算机科学 2024-08-20 Zhiqiang Wang , Xinyue Yu , Qianli Huang , Yongguang Gong