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 1709.01604cs.CRcs.LGstat.ML
收藏

机器学习中的隐私风险:分析与过度拟合的联系

Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting

Carnegie Mellon University(卡内基梅隆大学);University of Wisconsin–Madison(威斯康星大学麦迪逊分校)

Samuel Yeom, Irene Giacomelli, Matt Fredrikson, Somesh Jha

摘要:

当机器学习算法应用于敏感数据时,会对隐私构成明显的威胁。越来越多的先前工作表明,由这些算法产生的模型可能会通过模型的结构或其可观察到的行为将训练数据中的特定私有信息泄露给攻击者。然而,这种隐私风险的根本原因并没有得到很好的理解,除了少数轶事,表明过度拟合和影响可能发挥作用。本文研究了过拟合和影响对攻击者从机器学习模型中学习有关训练数据的信息的能力的影响,无论是通过训练集成员推理还是属性推理攻击。使用正式和实证分析,我们说明了这些因素和隐私风险,出现在几个流行的机器学习算法之间的明确关系。我们发现,过拟合是足以让攻击者进行成员推理,当目标属性满足一定的条件,其影响,属性推理攻击。有趣的是,我们的正式分析还表明,过拟合对于这些攻击来说并不是必需的,并开始揭示其他因素可能在起作用。最后,我们探讨了成员推理和属性推理之间的联系,表明两者之间存在着深刻的联系,导致有效的新攻击。

英文摘要:

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to an attacker, either through the models' structure or their observable behavior. However, the underlying cause of this privacy risk is not well understood beyond a handful of anecdotal accounts that suggest overfitting and influence might play a role. This paper examines the effect that overfitting and influence have on the ability of an attacker to learn information about the training data from machine learning models, either through training set membership inference or attribute inference attacks. Using both formal and empirical analyses, we illustrate a clear relationship between these factors and the privacy risk that arises in several popular machine learning algorithms. We find that overfitting is sufficient to allow an attacker to perform membership inference and, when the target attribute meets certain conditions about its influence, attribute inference attacks. Interestingly, our formal analysis also shows that overfitting is not necessary for these attacks and begins to shed light on what other factors may be in play. Finally, we explore the connection between membership inference and attribute inference, showing that there are deep connections between the two that lead to effective new attacks.

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。

↑