Impact of Privacy Parameters on Deep Learning Models for Image Classification

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Chaulagain, Basanta
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909421361168384
author Chaulagain, Basanta
author_facet Chaulagain, Basanta
contents The project aims to develop differentially private deep learning models for image classification on CIFAR-10 datasets \cite{cifar10} and analyze the impact of various privacy parameters on model accuracy. We have implemented five different deep learning models, namely ConvNet, ResNet18, EfficientNet, ViT, and DenseNet121 and three supervised classifiers namely K-Nearest Neighbors, Naive Bayes Classifier and Support Vector Machine. We evaluated the performance of these models under varying settings. Our best performing model to date is EfficientNet with test accuracy of $59.63\%$ with the following parameters (Adam optimizer, batch size 256, epoch size 100, epsilon value 5.0, learning rate $1e-3$, clipping threshold 1.0, and noise multiplier 0.912).
format Preprint
id arxiv_https___arxiv_org_abs_2412_06689
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Impact of Privacy Parameters on Deep Learning Models for Image Classification
Chaulagain, Basanta
Machine Learning
Cryptography and Security
The project aims to develop differentially private deep learning models for image classification on CIFAR-10 datasets \cite{cifar10} and analyze the impact of various privacy parameters on model accuracy. We have implemented five different deep learning models, namely ConvNet, ResNet18, EfficientNet, ViT, and DenseNet121 and three supervised classifiers namely K-Nearest Neighbors, Naive Bayes Classifier and Support Vector Machine. We evaluated the performance of these models under varying settings. Our best performing model to date is EfficientNet with test accuracy of $59.63\%$ with the following parameters (Adam optimizer, batch size 256, epoch size 100, epsilon value 5.0, learning rate $1e-3$, clipping threshold 1.0, and noise multiplier 0.912).
title Impact of Privacy Parameters on Deep Learning Models for Image Classification
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2412.06689