arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.01538cs.CRcs.AIcs.DBcs.LG
收藏

通过差异审计实现数据来源

Data Provenance via Differential Auditing

Peng Cheng Laboratory(鹏城实验室);Singapore Management University(新加坡管理大学)

Xin Mu, Ming Pang, Feida Zhu

摘要:

审计数据来源(ADP),即,审核某段数据是否已用于训练机器学习模型是数据来源中的重要问题。这项任务的可行性已被现有的审计技术所证明,例如,影子审计方法,在某些条件下,如标签信息的可用性和目标模型的训练协议的知识。不幸的是,这两个条件在实际应用中通常都不具备。在本文中,我们介绍了通过差异审计的数据来源(DPDA),这是一个基于统计显著差异的不同方法审计数据来源的实用框架,即,经过精心设计的转换后,来自目标模型训练集的扰动输入数据将导致输出中的变化比来自模型非训练集的变化剧烈得多。该框架允许审计员区分训练数据和非训练数据,而不需要在标记的输出数据的帮助下训练任何阴影模型。此外,我们提出了两个有效的审计功能的实现,一个加法和乘法。我们报告评估真实世界的数据集证明我们提出的审计技术的有效性。

英文摘要:

Auditing Data Provenance (ADP), i.e., auditing if a certain piece of data has been used to train a machine learning model, is an important problem in data provenance. The feasibility of the task has been demonstrated by existing auditing techniques, e.g., shadow auditing methods, under certain conditions such as the availability of label information and the knowledge of training protocols for the target model. Unfortunately, both of these conditions are often unavailable in real applications. In this paper, we introduce Data Provenance via Differential Auditing (DPDA), a practical framework for auditing data provenance with a different approach based on statistically significant differentials, i.e., after carefully designed transformation, perturbed input data from the target model's training set would result in much more drastic changes in the output than those from the model's non-training set. This framework allows auditors to distinguish training data from non-training ones without the need of training any shadow models with the help of labeled output data. Furthermore, we propose two effective auditing function implementations, an additive one and a multiplicative one. We report evaluations on real-world data sets demonstrating the effectiveness of our proposed auditing technique.

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。

↑