成员推断测试:在目标分类模型中审计训练数据
Membership Inference Test: Auditing Training Data in Object Classification Models
AI总结:
本研究提出适用于目标分类模型的MINT架构,通过分析训练数据使用情况,实现70%-80%的识别精度,提升数据透明度。
摘要:
在本研究中,我们分析了成员推断测试(MINT)的性能,重点在于确定给定的数据是否在训练阶段被使用,特别是在目标识别领域。在目标识别领域,我们提出并开发了适用于MINT模型的架构。这些架构旨在优化数据利用的性能和效率,提供针对目标识别领域复杂性的定制解决方案。我们进行了涉及目标检测模型、嵌入提取器和MINT模块的实验。这些实验在三个公共数据库中进行,总共有超过174,000张图像。所提出的架构利用卷积层来捕捉和建模训练过程中数据中的激活模式。通过我们的分析,我们能够识别用于测试和训练的数据,实现的精确率范围在70%到80%之间,具体取决于所选择的检测模块层深度作为MINT模块的输入。此外,我们的研究还涉及对影响MINT模块的因素的分析,深入探讨了导致更透明训练过程的贡献因素。
英文摘要:
In this research, we analyze the performance of Membership Inference Tests (MINT), focusing on determining whether given data were utilized during the training phase, specifically in the domain of object recognition. Within the area of object recognition, we propose and develop architectures tailored for MINT models. These architectures aim to optimize performance and efficiency in data utilization, offering a tailored solution to tackle the complexities inherent in the object recognition domain. We conducted experiments involving an object detection model, an embedding extractor, and a MINT module. These experiments were performed in three public databases, totaling over 174K images. The proposed architecture leverages convolutional layers to capture and model the activation patterns present in the data during the training process. Through our analysis, we are able to identify given data used for testing and training, achieving precision rates ranging between 70% and 80%, contingent upon the depth of the detection module layer chosen for input to the MINT module. Additionally, our studies entail an analysis of the factors influencing the MINT Module, delving into the contributing elements behind more transparent training processes.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。