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).

翻译：本项目旨在为CIFAR-10数据集\cite{cifar10}开发差分隐私深度学习图像分类模型，并分析不同隐私参数对模型准确率的影响。我们实现了五种不同的深度学习模型（ConvNet、ResNet18、EfficientNet、ViT和DenseNet121）以及三种监督分类器（K近邻、朴素贝叶斯分类器和支持向量机）。我们在不同参数设置下评估了这些模型的性能。目前表现最佳的模型是EfficientNet，在以下参数配置下（Adam优化器、批大小256、训练轮数100、ε值5.0、学习率$1e-3$、梯度裁剪阈值1.0、噪声乘数0.912）取得了$59.63\%$的测试准确率。