中文
相关论文

相关论文: Perfectly Accurate Membership Inference by a Disho…

200 篇论文

In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally. However, recent work shows that client's private information…

机器学习 · 计算机科学 2021-11-02 Oualid Zari , Chuan Xu , Giovanni Neglia

Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…

密码学与安全 · 计算机科学 2024-12-10 Li Bai , Haibo Hu , Qingqing Ye , Haoyang Li , Leixia Wang , Jianliang Xu

Federated learning (FL) was originally regarded as a framework for collaborative learning among clients with data privacy protection through a coordinating server. In this paper, we propose a new active membership inference (AMI) attack…

机器学习 · 计算机科学 2023-08-30 Truc Nguyen , Phung Lai , Khang Tran , NhatHai Phan , My T. Thai

Federated Learning (FL) enables collaborative model training without centralizing client data, making it attractive for privacy-sensitive domains. While existing approaches employ cryptographic techniques such as homomorphic encryption,…

密码学与安全 · 计算机科学 2026-02-09 Sahar Ghoflsaz Ghinani , Elaheh Sadredini

Federated learning is a prominent framework that enables clients (e.g., mobile devices or organizations) to train a collaboratively global model under a central server's orchestration while keeping local training datasets' privacy. However,…

机器学习 · 计算机科学 2021-07-20 Farnaz Tahmasebian , Jian Lou , Li Xiong

Recent studies propose membership inference (MI) attacks on deep models, where the goal is to infer if a sample has been used in the training process. Despite their apparent success, these studies only report accuracy, precision, and recall…

机器学习 · 计算机科学 2021-03-24 Shahbaz Rezaei , Xin Liu

Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients collaborate in learning a global encoder using unlabeled data,…

密码学与安全 · 计算机科学 2024-04-29 Kongyang Chen , Wenfeng Wang , Zixin Wang , Wangjun Zhang , Zhipeng Li , Yao Huang

Machine learning models used for distributed architectures consisting of servers and clients require large amounts of data to achieve high accuracy. Data obtained from clients are collected on a central server for model training. However,…

密码学与安全 · 计算机科学 2025-09-18 Ozer Ozturk , Busra Buyuktanir , Gozde Karatas Baydogmus , Kazim Yildiz

Federated Learning is a machine learning setting that reduces direct data exposure, improving the privacy guarantees of machine learning models. Yet, the exchange of model updates between the participants and the aggregator can still leak…

机器学习 · 计算机科学 2025-12-18 Pablo Montaña-Fernández , Ines Ortega-Fernandez

Membership inference (MI) attack is currently the most popular test for measuring privacy leakage in machine learning models. Given a machine learning model, a data point and some auxiliary information, the goal of an MI attack is to…

机器学习 · 计算机科学 2023-03-09 Zhifeng Kong , Amrita Roy Chowdhury , Kamalika Chaudhuri

Federated learning has become a widely used paradigm for collaboratively training a common model among different participants with the help of a central server that coordinates the training. Although only the model parameters or other model…

密码学与安全 · 计算机科学 2023-10-31 Raouf Kerkouche , Gergely Ács , Mario Fritz

Federated learning is a privacy-focused approach towards machine learning where models are trained on client devices with locally available data and aggregated at a central server. However, the dependence on a single central server is…

机器学习 · 计算机科学 2026-01-06 Shamik Bhattacharyya , Rachel Kalpana Kalaimani

While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…

密码学与安全 · 计算机科学 2020-09-11 Yang Zou , Zhikun Zhang , Michael Backes , Yang Zhang

Recent studies have revealed that federated learning (FL), once considered secure due to clients not sharing their private data with the server, is vulnerable to attacks such as client-side training data distribution inference, where a…

密码学与安全 · 计算机科学 2024-04-05 Yichang Xu , Ming Yin , Minghong Fang , Neil Zhenqiang Gong

Distributed machine learning generally aims at training a global model based on distributed data without collecting all the data to a centralized location, where two different approaches have been proposed: collecting and aggregating local…

机器学习 · 计算机科学 2020-07-08 Hanlin Lu , Changchang Liu , Ting He , Shiqiang Wang , Kevin S. Chan

Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wherein FL clients are subject to adversarial (Byzantine) attacks, while the FL server is trusted…

机器学习 · 计算机科学 2026-04-30 Emmanouil Kritharakis , Dusan Jakovetic , Antonios Makris , Konstantinos Tserpes

Aiming at privacy preservation, Federated Learning (FL) is an emerging machine learning approach enabling model training on decentralized devices or data sources. The learning mechanism of FL relies on aggregating parameter updates from…

机器学习 · 计算机科学 2024-05-21 Jiayan Chen , Zhirong Qian , Tianhui Meng , Xitong Gao , Tian Wang , Weijia Jia

Federated Learning (FL) is a distributed machine learning paradigm facilitating participants to collaboratively train a model without revealing their local data. However, when FL is deployed into the wild, some intelligent clients can…

机器学习 · 计算机科学 2025-10-03 Andrea Augello , Ashish Gupta , Giuseppe Lo Re , Sajal K. Das

Secure aggregation is a cryptographic protocol that securely computes the aggregation of its inputs. It is pivotal in keeping model updates private in federated learning. Indeed, the use of secure aggregation prevents the server from…

机器学习 · 计算机科学 2022-09-07 Dario Pasquini , Danilo Francati , Giuseppe Ateniese

Federated learning is a promising distributed learning paradigm that enables collaborative model training without exposing local client data, thereby protecting data privacy. However, it also brings new threats and challenges. The…

密码学与安全 · 计算机科学 2026-04-14 Nina Cai , Jinguang Han , Weizhi Meng
‹ 上一页 1 2 3 10 下一页 ›