arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.07902cs.LGcs.CRstat.ML
收藏

对抗性表示学习在信息混淆中的权衡与保证

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation

Carnegie Mellon University(卡内基梅隆大学);D. E. Shaw & Co.(D.E.肖公司);University of Virginia(弗吉尼亚大学);Microsoft Research Montreal(微软研究院蒙特利尔分院)

Han Zhao, Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon

摘要:

机器学习服务中使用的众包数据可能携带有关用户不想共享的属性的敏感信息。已经提出了各种方法来最小化敏感属性的潜在信息泄漏,同时最大化任务精度。然而,人们对这些方法背后的理论知之甚少。鉴于这一差距,我们开发了一个新的理论框架属性混淆。在我们的框架下,我们提出了一个极大极小优化配方,以保护给定的属性,并分析其推理保证对最坏情况下的对手。同时,很明显,一般来说,在最小化信息泄漏和最大化任务准确性之间存在着紧张关系。为了理解这一点,我们证明了一个信息理论的下限,以精确地描述准确性和信息泄漏之间的基本权衡。我们在两个真实世界的数据集上进行实验,以证实推理保证并验证这种权衡。我们的研究结果表明,在几种替代方案中,对抗学习方法在属性混淆和准确性最大化方面实现了最佳权衡。

英文摘要:

Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes while maximizing the task accuracy. However, little is known about the theory behind these methods. In light of this gap, we develop a novel theoretical framework for attribute obfuscation. Under our framework, we propose a minimax optimization formulation to protect the given attribute and analyze its inference guarantees against worst-case adversaries. Meanwhile, it is clear that in general there is a tension between minimizing information leakage and maximizing task accuracy. To understand this, we prove an information-theoretic lower bound to precisely characterize the fundamental trade-off between accuracy and information leakage. We conduct experiments on two real-world datasets to corroborate the inference guarantees and validate this trade-off. Our results indicate that, among several alternatives, the adversarial learning approach achieves the best trade-off in terms of attribute obfuscation and accuracy maximization.

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。

↑