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 2002.06856cs.LGstat.ML
收藏

成员推断攻击的数据和模型相关性

Data and Model Dependencies of Membership Inference Attack

Data61, CSIRO(澳大利亚联邦科学与工业研究组织 Data61);University of Melbourne(墨尔本大学);Macquarie University(麦考瑞大学)

Shakila Mahjabin Tonni, Dinusha Vatsalan, Farhad Farokhi, Dali Kaafar, Zhigang Lu, Gioacchino Tangari

摘要:

机器学习(ML)模型已被证明易受成员推断攻击(MIA)的攻击,MIA通过观察ML模型的预测输出来推断目标数据集中给定数据点的成员资格。虽然MIA成功的关键因素尚未完全了解,但现有的防御机制(如使用L2正则化\cite{10shokri2017membership}和dropout层\cite{salem2018ml})仅考虑模型的过拟合特性。在本文中,我们提供了一个实证分析的数据和ML模型属性的ML技术的脆弱性MIA的影响。我们的研究结果揭示了MIA精度与数据集和训练模型的属性之间的关系。特别是,我们表明,阴影数据集的大小,类和特征的平衡和目标数据集的熵,训练模型的配置和公平性是最有影响力的因素。基于这些实验结果,我们得出结论,随着模型过拟合,多个属性共同有助于MIA的成功,而不是任何单一的属性。基于我们的实验发现,我们建议使用这些数据和模型属性作为正则化器来保护ML模型免受MIA的影响。我们的研究结果表明,所提出的防御机制可以降低MIA的准确性高达25%,而不牺牲ML模型的预测效用。

英文摘要:

Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by observing the prediction output of the ML model. While the key factors for the success of MIA have not yet been fully understood, existing defense mechanisms such as using L2 regularization \cite{10shokri2017membership} and dropout layers \cite{salem2018ml} take only the model's overfitting property into consideration. In this paper, we provide an empirical analysis of the impact of both the data and ML model properties on the vulnerability of ML techniques to MIA. Our results reveal the relationship between MIA accuracy and properties of the dataset and training model in use. In particular, we show that the size of shadow dataset, the class and feature balance and the entropy of the target dataset, the configurations and fairness of the training model are the most influential factors. Based on those experimental findings, we conclude that along with model overfitting, multiple properties jointly contribute to MIA success instead of any single property. Building on our experimental findings, we propose using those data and model properties as regularizers to protect ML models against MIA. Our results show that the proposed defense mechanisms can reduce the MIA accuracy by up to 25\% without sacrificing the ML model prediction utility.

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。

↑