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 2102.01502cs.CRcs.AIcs.CLcs.LG
收藏

ADePT:基于自动编码器的差分私有文本转换

ADePT: Auto-encoder based Differentially Private Text Transformation

Amazon Alexa(亚马逊Alexa)

Satyapriya Krishna, Rahul Gupta, Christophe Dupuy

摘要:

在对包含个人信息的数据建立统计模型时,隐私是一个重要的问题。差分隐私提供了隐私的强定义,并且可以用于解决若干隐私问题(Dwork等人,2014年)。对于包含敏感信息的数据集的差分私有变换,已经提出了多种解决方案。然而,由于过程中添加的噪声,这种变换算法在自然语言处理(NLP)任务中提供较差的实用性。在本文中,我们解决这个问题,提供了一个实用程序保持差分私有文本转换算法,使用自动编码器。我们的算法转换文本以提供对攻击的鲁棒性,并产生具有高语义质量的转换,在下游NLP任务中表现良好。我们证明了我们算法的理论隐私保证,并评估了其在成员推断攻击(MIA)下的隐私泄露情况(Shokri等人,2017年)使用转换数据训练的模型。我们的研究结果表明,该模型对MIA攻击的表现更好,同时提供较低或没有退化的底层转换过程的效用相比,现有的基线。

英文摘要:

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014). Multiple solutions have been proposed for the differentially-private transformation of datasets containing sensitive information. However, such transformation algorithms offer poor utility in Natural Language Processing (NLP) tasks due to noise added in the process. In this paper, we address this issue by providing a utility-preserving differentially private text transformation algorithm using auto-encoders. Our algorithm transforms text to offer robustness against attacks and produces transformations with high semantic quality that perform well on downstream NLP tasks. We prove the theoretical privacy guarantee of our algorithm and assess its privacy leakage under Membership Inference Attacks(MIA) (Shokri et al., 2017) on models trained with transformed data. Our results show that the proposed model performs better against MIA attacks while offering lower to no degradation in the utility of the underlying transformation process compared to existing baselines.

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。

↑