当前位置: X-MOL 学术IEEE Trans. Inform. Forensics Secur. › 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.)
Developing Non-Stochastic Privacy-Preserving Policies Using Agglomerative Clustering
IEEE Transactions on Information Forensics and Security ( IF 6.8 ) Pub Date : 2020-06-15 , DOI: 10.1109/tifs.2020.3002479
Ni Ding , Farhad Farokhi

We consider a non-stochastic privacy-preserving problem in which an adversary aims to infer sensitive information ${S}$ from publicly accessible data ${X}$ without using statistics. We consider the problem of generating and releasing a quantization $\hat {X}$ of ${X}$ to minimize the privacy leakage of ${S}$ to $\hat {X}$ while maintaining a certain level of utility (or, inversely, the quantization loss). The variables ${S}$ and ${X}$ are treated as bounded and non-probabilistic, but are otherwise general. We consider two existing non-stochastic privacy measures, namely the maximum uncertainty reduction ${L}_{0}({S} \rightarrow \hat {{X}})$ and the refined information ${I}_{*}({S}; \hat {{X}})$ (also called the maximin information) of ${S}$ . For each privacy measure, we propose a corresponding agglomerative clustering algorithm that converges to a locally optimal quantization solution $\hat {{X}}$ by iteratively merging elements in the alphabet of ${X}$ . To instantiate the solution to this problem, we consider two specific utility measures, the worst-case resolution of ${X}$ by observing $\hat {{X}}$ and the maximal distortion of the released data $\hat {{X}}$ . We show that the value of the maximin information ${I}_{*}({S}; \hat {{X}})$ can be determined by dividing the confusability graph into connected subgraphs. Hence, ${I}_{*}({S}; \hat {{X}})$ can be reduced by merging nodes connecting subgraphs. The relation to the probabilistic information-theoretic privacy is also studied by noting that the Gács-Körner common information is the stochastic version of ${I}_{*}$ and indicates the attainability of statistical indistinguishability.

中文翻译:

使用聚集群集开发非随机性的隐私保护策略

我们考虑一个非随机性的隐私保护问题,其中对手旨在推断敏感信息 $ {S} $ 从公开访问的数据 $ {X} $ 不使用统计信息。我们考虑生成和释放量化的问题 $ \ hat {X} $ $ {X} $ 最大限度地减少隐私泄露 $ {S} $ $ \ hat {X} $ 同时保持一定程度的效用(或反之,量化损失)。变量 $ {S} $ $ {X} $ 被视为有界且非概率性的,但在其他方面则是一般性的。我们考虑了两种现有的非随机隐私措施,即最大不确定性降低 $ {L} _ {0}({S} \ rightarrow \ hat {{X}})$ 和完善的信息 $ {I} _ {*}({S}; \ hat {{X}})$ (也称为最大化信息) $ {S} $ 。对于每种隐私措施,我们提出一种对应的聚集聚类算法,该算法可以收敛到局部最优量化解决方案 $ \ hat {{X}} $ 通过迭代合并字母中的元素 $ {X} $ 。为了实例化此问题的解决方案,我们考虑了两个具体的实用措施,即最坏情况下的解决方案。 $ {X} $ 通过观察 $ \ hat {{X}} $ 以及释放数据的最大失真 $ \ hat {{X}} $ 。我们证明了最大化信息的价值 $ {I} _ {*}({S}; \ hat {{X}})$ 可以通过将可混淆性图划分为相连的子图来确定。因此, $ {I} _ {*}({S}; \ hat {{X}})$ 可以通过合并连接子图的节点来减少。还通过指出Gács-Körner共同信息是随机信息的形式来研究与概率信息理论隐私的关系。 $ {I} _ {*} $ 并指出统计上不可区分的可达到性。
更新日期:2020-07-21
down
wechat
bug