论文标题
来自模型的数据：从非运动和鲁棒模型中提取数据
Data from Model: Extracting Data from Non-robust and Robust Models
论文作者
论文摘要
深度学习的本质是利用数据来培训深度神经网络（DNN）模型。这项工作探讨了从模型生成数据的反向过程，试图揭示数据与模型之间的关系。我们通过序列重复数据的过程（DTM）和来自模型（DFM）的数据，并通过测量原始验证数据集的精度下降来探索特征映射信息的丢失。我们对非稳定和鲁棒的起源模型执行此实验。我们的结果表明，即使在多个DTM和DFM序列之后，精度下降也受到限制，尤其是对于健壮的模型。这种循环转换的成功可以归因于数据和模型中存在的共享特征映射。使用相同的数据，我们观察到不同的DTM过程会导致具有不同功能的模型，尤其是对于不同的网络体系结构家族，即使它们实现了可比的性能。
The essence of deep learning is to exploit data to train a deep neural network (DNN) model. This work explores the reverse process of generating data from a model, attempting to reveal the relationship between the data and the model. We repeat the process of Data to Model (DtM) and Data from Model (DfM) in sequence and explore the loss of feature mapping information by measuring the accuracy drop on the original validation dataset. We perform this experiment for both a non-robust and robust origin model. Our results show that the accuracy drop is limited even after multiple sequences of DtM and DfM, especially for robust models. The success of this cycling transformation can be attributed to the shared feature mapping existing in data and model. Using the same data, we observe that different DtM processes result in models having different features, especially for different network architecture families, even though they achieve comparable performance.
