当前位置: X-MOL 学术arXiv.cs.PL › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deciding Accuracy of Differential Privacy Schemes
arXiv - CS - Programming Languages Pub Date : 2020-11-12 , DOI: arxiv-2011.06404
Gilles Barthe and Rohit Chadha and Paul Krogmeier and A. Prasad Sistla and Mahesh Viswanathan

Differential privacy is a mathematical framework for developing statistical computations with provable guarantees of privacy and accuracy. In contrast to the privacy component of differential privacy, which has a clear mathematical and intuitive meaning, the accuracy component of differential privacy does not have a generally accepted definition; accuracy claims of differential privacy algorithms vary from algorithm to algorithm and are not instantiations of a general definition. We identify program discontinuity as a common theme in existing \emph{ad hoc} definitions and introduce an alternative notion of accuracy parametrized by, what we call, {\distance} -- the {\distance} of an input $x$ w.r.t., a deterministic computation $f$ and a distance $d$, is the minimal distance $d(x,y)$ over all $y$ such that $f(y)\neq f(x)$. We show that our notion of accuracy subsumes the definition used in theoretical computer science, and captures known accuracy claims for differential privacy algorithms. In fact, our general notion of accuracy helps us prove better claims in some cases. Next, we study the decidability of accuracy. We first show that accuracy is in general undecidable. Then, we define a non-trivial class of probabilistic computations for which accuracy is decidable (unconditionally, or assuming Schanuel's conjecture). We implement our decision procedure and experimentally evaluate the effectiveness of our approach for generating proofs or counterexamples of accuracy for common algorithms from the literature.

中文翻译:

确定差异隐私方案的准确性

差分隐私是一个数学框架,用于开发具有可证明的隐私和准确性保证的统计计算。相对于差分隐私的隐私分量具有明确的数学和直观意义,差分隐私的准确性分量没有一个普遍接受的定义;差分隐私算法的准确性要求因算法而异,并且不是一般定义的实例。我们将程序不连续性确定为现有 \emph{ad hoc} 定义中的一个共同主题,并引入了另一种精度概念,其参数化为我们所说的 {\distance} - 输入 $x$ wrt 的 {\distance},确定性计算 $f$ 和距离 $d$,是所有 $y$ 的最小距离 $d(x,y)$,使得 $f(y)\neq f(x)$。我们表明,我们的准确性概念包含了理论计算机科学中使用的定义,并捕获了差异隐私算法的已知准确性声明。事实上,我们对准确性的一般概念有助于我们在某些情况下证明更好的主张。接下来,我们研究准确性的可判定性。我们首先表明准确性通常是不可判定的。然后,我们定义了一类非平凡的概率计算,其准确性是可判定的(无条件地,或假设 Schanuel 的猜想)。我们实施我们的决策程序,并通过实验评估我们的方法的有效性,以从文献中为常见算法生成准确性的证明或反例。我们对准确性的一般概念有助于我们在某些情况下证明更好的主张。接下来,我们研究准确性的可判定性。我们首先表明准确性通常是不可判定的。然后,我们定义了一类非平凡的概率计算,其准确性是可判定的(无条件地,或假设 Schanuel 的猜想)。我们实施我们的决策程序,并通过实验评估我们的方法的有效性,以从文献中为常见算法生成准确性的证明或反例。我们对准确性的一般概念有助于我们在某些情况下证明更好的主张。接下来,我们研究准确性的可判定性。我们首先表明准确性通常是不可判定的。然后,我们定义了一类非平凡的概率计算,其准确性是可判定的(无条件地,或假设 Schanuel 的猜想)。我们实施我们的决策程序,并通过实验评估我们的方法的有效性,以从文献中为常见算法生成准确性的证明或反例。
更新日期:2020-11-13
down
wechat
bug