Salvato in:
Dettagli Bibliografici
Autori principali: Aguilera-Martínez, Francisco, Berzal, Fernando
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2409.17144
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914957164019712
author Aguilera-Martínez, Francisco
Berzal, Fernando
author_facet Aguilera-Martínez, Francisco
Berzal, Fernando
contents Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD] requires the modification of the standard stochastic gradient descent [SGD] algorithm for training new models. In this short paper, a novel regularization strategy is proposed to achieve the same goal in a more efficient manner.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17144
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Differential Privacy Regularization: Protecting Training Data Through Loss Function Regularization
Aguilera-Martínez, Francisco
Berzal, Fernando
Machine Learning
Artificial Intelligence
Cryptography and Security
Neural and Evolutionary Computing
Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD] requires the modification of the standard stochastic gradient descent [SGD] algorithm for training new models. In this short paper, a novel regularization strategy is proposed to achieve the same goal in a more efficient manner.
title Differential Privacy Regularization: Protecting Training Data Through Loss Function Regularization
topic Machine Learning
Artificial Intelligence
Cryptography and Security
Neural and Evolutionary Computing
url https://arxiv.org/abs/2409.17144