It is a growing direction to utilize unintended memorization in ML models to benefit real-world applications, with recent efforts like user auditing, dataset ownership inference and forgotten data measurement. Standing on the point of ML model development, we introduce a process named data origin inference, to assist ML developers in locating missed or faulty data origin in training set without maintaining strenuous metadata. We formally define the data origin and the data origin inference task in the development of the ML model (mainly neural networks). Then we propose a novel inference strategy combining embedded-space multiple instance classification and shadow training. Diverse use cases cover language, visual and structured data, with various kinds of data origin (e.g. business, county, movie, mobile user, text author). A comprehensive performance analysis of our proposed strategy contains referenced target model layers, available testing data for each origin, and in shadow training, the implementations of feature extraction as well as shadow models. Our best inference accuracy achieves 98.96% in the language use case when the target model is a transformer-based deep neural network. Furthermore, we give a statistical analysis of different kinds of data origin to investigate what kind of origin is probably to be inferred correctly.

翻译：利用机器学习模型中的无意记忆来造福实际应用是一个日益增长的研究方向，近期的工作包括用户审计、数据集所有权推断和遗忘数据测量。从机器学习模型开发的角度出发，我们引入了一个名为数据来源推断的过程，旨在帮助机器学习开发者在不维护繁琐元数据的情况下，定位训练集中缺失或错误的数据来源。我们正式定义了机器学习模型（主要是神经网络）开发中的数据来源及数据来源推断任务。随后，我们提出了一种新颖的推断策略，结合了嵌入空间的多实例分类和影子训练。多样化的应用场景涵盖语言、视觉和结构化数据，涉及多种类型的数据来源（如企业、县、电影、移动用户、文本作者）。对我们所提策略的综合性能分析包括参考的目标模型层、每个来源可用的测试数据，以及在影子训练中特征提取和影子模型的实现。在目标模型为基于Transformer的深度神经网络的语言场景中，我们的最佳推断准确率达到了98.96%。此外，我们对不同类型的数据来源进行了统计分析，以探究哪些类型的数据来源可能被正确推断。