copy and paste this google map to your website or blog!
Press copy button and paste into your blog or website.
(Please switch to 'HTML' mode when posting into your blog. Examples: WordPress Example, Blogger Example)
Comprehensive Analysis of Privacy Leakage in Vertical Federated . . . Abstract: Vertical federated learning (VFL), a variant of federated learning, has recently attracted increasing attention An active party having the true labels jointly trains a model with other parties (referred to as passive parties) in order to use more features to achieve higher model accuracy
PoPETs Proceedings — Volume 2022 - petsymposium. org Comprehensive Analysis of Privacy Leakage in Vertical Federated Learning During Prediction [PDF] Xue Jiang (Technical University of Munich; Huawei Technologies Düsseldorf GmbH), Xuebing Zhou (Huawei Technologies Düsseldorf GmbH), Jens Grossklags (Technical University of Munich)
User-Level Label Leakage from Gradients in Federated Learning User-Level Label Leakage from Gradients in Federated Learning Abstract: Federated learning enables multiple users to 1 Introduction ents), while their raw data remains local on their de-vices In contrast to the common belief that this pro-vides privacy benefits, we here add to the very re-ce
PoPETs Proceedings — Towards Sparse Federated Analytics: Location . . . Keywords: federated analytics, location privacy, differential privacy, secure aggregation Copyright in PoPETs articles are held by their authors This article is published under a Creative Commons Attribution-NonCommercial-NoDerivs 3 0 license
Comprehensive Analysis of Privacy Leakage in Vertical Federated . . . Keywords: vertical federated learning, privacy attacks DOI 10 2478 popets-2022-0045 Received 2021-08-31; revised 2021-12-15; accepted 2021-12-16 *Corresponding Author: Xue Jiang: Technical University of Munich; Huawei Technologies Düsseldorf GmbH, E-mail: xue jiang@tum de
Privacy-Preserving High-dimensional Data Collection with Federated . . . ata synthesis, we propose DP-Fed-Wae, an effi-cient privacy-preserving framework for collecting high-dimensional categorical data With the combination of a generative autoencoder, federated learning, and dif-ferential privacy, our framework is capable of privately learning the statistical distri
Towards Sparse Federated Analytics: Location Heatmaps under Distributed . . . Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation alized data from millions of user devices It aims to ensure dif-ferential privacy before data becomes visible to a ser-vice provider while maintaining high data accuracy and minimizing resource consumption on users’ devices
Privacy-Preserving High-dimensional Data Collection with Federated . . . With the combination of a generative autoencoder, federated learning, and differential privacy, our framework is capable of privately learning the statistical distributions of local data and generating high utility synthetic data on the server side without revealing users’ private information
PoPETs Proceedings — AriaNN: Low-Interaction Privacy-Preserving Deep . . . Last, we propose an extension to support n-party private federated learning We implement our framework as an extensible system on top of PyTorch that leverages CPU and GPU hardware acceleration for cryptographic and machine learning operations