paper-with-me

Papers

Decentralized Collaborative Learning Framework with External Privacy Leakage Analysis

2024-04-01 · Tsuyoshi Idé, Dzung T. Phan, Rudy Raymond

This paper presents two methodological advancements in decentralized multi-task learning under privacy constraints, aiming to pave the way for future developments in next-generation Blockchain platforms. First, we expand the existing framework for collaborative dictionary learning (CollabDict), which has previously been limited to Gaussian mixture models, by incorporating deep variational autoencoders (VAEs) into the framework, with a particular focus on anomaly detection. We demonstrate that the VAE-based anomaly score function shares the same mathematical structure as the non-deep model, and provide comprehensive qualitative comparison. Second, considering the widespread use of "pre-trained models," we provide a mathematical analysis on data privacy leakage when models trained with CollabDict are shared externally. We show that the CollabDict approach, when applied to Gaussian mixtures, adheres to a Renyi differential privacy criterion. Additionally, we propose a practical metric for monitoring internal privacy breaches during the learning process.

📄 PDF Abstract BibTeX arXiv:2404.01270

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly DetectionDictionary LearningMulti-Task Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defenses

2024-11-05 · Isaac Baglin, Xiatian Zhu, Simon Hadfield

Federated Learning is a privacy preserving decentralized machine learning paradigm designed to collaboratively train models across multiple clients by exchanging gradients to the server and keeping private data local. Ne…

Federated LearningPrivacy Preserving

FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning

2025-03-08 · Mingcong Xu, Xiaojin Zhang, Wei Chen, Hai Jin

Federated Learning (FL) enables collaborative training of models across distributed clients without sharing local data, addressing privacy concerns in decentralized systems. However, the gradient-sharing process exposes …

Federated LearningPrivacy Preserving

Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentation

2022-08-22 · Holger R. Roth, Ali Hatamizadeh, Ziyue Xu, Can Zhao 외

Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be beneficial as it allows institutes with …

Brain Tumor SegmentationImage SegmentationSegmentationSemantic Segmentation+1

Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networks

2024-06-06 · Rajarshi Saha, Mohamed Seif, Michal Yemini, Andrea J. Goldsmith 외

We consider the problem of privately estimating the mean of vectors distributed across different nodes of an unreliable wireless network, where communications between nodes can fail intermittently. We adopt a semi-decent…

Privacy Preserving

Mitigating Leakage from Data Dependent Communications in Decentralized Computing using Differential Privacy

2021-12-23 · Riad Ladjel, Nicolas Anciaux, Aurélien Bellet, Guillaume Scerri

Imagine a group of citizens willing to collectively contribute their personal data for the common good to produce socially useful information, resulting from data analytics or machine learning computations. Sharing raw p…