Impact of Privacy Parameters on Deep Learning Models for Image Classification
This work addresses privacy concerns in image classification for machine learning practitioners, but it is incremental as it applies existing methods to analyze parameter impacts without introducing new techniques.
The study tackled the problem of developing differentially private deep learning models for image classification on CIFAR-10, analyzing how privacy parameters affect accuracy, with EfficientNet achieving a test accuracy of 59.63% under specific settings.
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).