XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning

2020-06-09 · MyungJae Shin, Chihoon Hwang, Joongheon Kim, Jihong Park, Mehdi Bennis, Seong-Lyun Kim

User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we develop a privacy-preserving XOR based mixup data augmentation technique, coined XorMixup, and thereby propose a novel one-shot FL framework, termed XorMixFL. The core idea is to collect other devices' encoded data samples that are decoded only using each device's own data samples. The decoding provides synthetic-but-realistic samples until inducing an IID dataset, used for model training. Both encoding and decoding procedures follow the bit-wise XOR operations that intentionally distort raw samples, thereby preserving data privacy. Simulation results corroborate that XorMixFL achieves up to 17.6% higher accuracy than Vanilla FL under a non-IID MNIST dataset.

📄 PDF Abstract BibTeX arXiv:2006.05148

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation Federated LearningPrivacy Preserving

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release

2022-02-14 · Donghao Li, Yang Cao, Yuan YAO

Privacy-preserving data release algorithms have gained increasing attention for their ability to protect user privacy while enabling downstream machine learning tasks. However, the utility of current popular algorithms i…

Data Augmentation Privacy Preserving Self-Supervised Learning

AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning

2021-05-02 · Yusuke Koda, Jihong Park, Mehdi Bennis, Praneeth Vepakomma 외

Wireless channels can be inherently privacy-preserving by distorting the received signals due to channel noise, and superpositioning multiple signals over-the-air. By harnessing these natural distortions and superpositio…

BIG-bench Machine Learning Data Augmentation Privacy Preserving

Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack

2024-03-14 · Yinggui Wang, Yuanqing Huang, Jianshu Li, Le Yang 외

The utilization of personal sensitive data in training face recognition (FR) models poses significant privacy concerns, as adversaries can employ model inversion attacks (MIA) to infer the original training data. Existin…

Data Augmentation Face Recognition Privacy Preserving

FedMix: Approximation of Mixup under Mean Augmented Federated Learning

2021-07-01 · ICLR 2021 1 · Tehrim Yoon, Sumin Shin, Sung Ju Hwang, Eunho Yang

Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to store data globally. While there are promisi…

Data Augmentation Federated Learning

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

2021-03-02 · Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl 외

Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP) training methods, although this comes …

Data Poisoning