arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.00482cs.ITmath.IT
收藏

一种基于失真的推理保护方法

A Distortion Based Approach for Protecting Inferences

Chi-Yo Tsai, Gaurav Kumar Agarwal, Christina Fragouli, Suhas Diggavi

摘要:

在推理系统中,Eudrop攻击的目的不是学习原始数据,而是学习系统推理来预测和操纵系统动作。我们认为,传统的信息安全措施可以是模糊的对手的估计能力,而不是采用基于失真的框架,使操作的度量空间。我们表明,需要完美的基于失真的安全性是更节俭的比需要完美的信息理论的保密性,即使是块长度为1的代码,在某些情况下提供无限的收益。在这个框架内,我们设计的算法,使有效地使用共享的随机性,并表明,共享随机密钥的每一位是指数有用的安全。

英文摘要:

Eavesdropping attacks in inference systems aim to learn not the raw data, but the system inferences to predict and manipulate system actions. We argue that conventional information security measures can be ambiguous on the adversary's estimation abilities, and adopt instead a distortion based framework that enables to operate over a metric space. We show that requiring perfect distortion-based security is more frugal than requiring perfect information-theoretic secrecy even for block length one codes, offering in some cases unbounded gains. Within this framework, we design algorithms that enable to efficiently use shared randomness, and show that each bit of shared random key is exponentially useful in security.

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。

↑