DPGen: Automated Program Synthesis for Differential Privacy

DPGen: Automated Program Synthesis for Differential Privacy
复制标题

DPGen:差异隐私的自动程序合成

DOI:
10.1145/3460120.3484781
复制
发表时间:
2021
期刊:
Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security
影响因子:
--
通讯作者:
Zhang, Danfeng
Zhang, Danfeng
中科院分区:
--
文献类型:
--
作者:
Wang, Yuxin;Ding, Zeyu;Xiao, Yingtai;Kifer, Daniel;Zhang, Danfeng

文献摘要

参考文献

被引文献

相似文献

差异隐私已成为以保护隐私的方式发布数据的事实上的标准。创建差分私有算法通常是从无噪声(非私有)算法开始的过程。然后,设计师决定在哪里添加噪音,以及添加多少噪音。这可能是一个不平凡的过程--如果不小心,算法可能会侵犯差分隐私或实用性较低。在本文中,我们提出了一种程序合成器DPGen,它接受非私有代码(没有任何噪声),并自动合成其差分私有版本(带有仔细校准的噪声)。在引擎盖下,DPGen使用新颖的算法自动生成带有噪声候选位置的草图程序,然后在草图程序上同时优化隐私保护和噪声尺度。此外,DPGen可以合成复杂的机制,这些机制可以自适应地处理查询,直到指定的隐私预算耗尽。在标准基准上进行评估时,DPGen能够在120秒内生成优化简单实用函数的不同私有机制。它也足够强大,可以合成自适应隐私机制。
Differential privacy has become a de facto standard for releasing data in a privacy-preserving way. Creating a differentially private algorithm is a process that often starts with a noise-free (non-private) algorithm. The designer then decides where to add noise, and how much of it to add. This can be a non-trivial process -- if not done carefully, the algorithm might either violate differential privacy or have low utility.In this paper, we present DPGen, a program synthesizer that takes in non-private code (without any noise) and automatically synthesizes its differentially private version (with carefully calibrated noise). Under the hood, DPGen uses novel algorithms to automatically generate a sketch program with candidate locations for noise, and then optimize privacy proof and noise scales simultaneously on the sketch program. Moreover, DPGen can synthesize sophisticated mechanisms that adaptively process queries until a specified privacy budget is exhausted. When evaluated on standard benchmarks, DPGen is able to generate differentially private mechanisms that optimize simple utility functions within 120 seconds. It is also powerful enough to synthesize adaptive privacy mechanisms.
DOI: 10.1145/1111037.1111045
发表时间: 2006-01
期刊: --
影响因子: --
作者:
Sebastian Hunt;David Sands
通讯作者: Sebastian Hunt;David Sands
DOI: 10.1145/3341698
发表时间: 2019
影响因子: --
作者:
Calvin Smith;Aws Albarghouthi
通讯作者: Aws Albarghouthi
DOI: 10.1145/3158146
发表时间: 2018-01-01
影响因子: 1.8
作者:
Albarghouthi, Aws;Hsu, Justin
通讯作者: Hsu, Justin
DOI: 10.1109/sp40001.2021.00060
发表时间: 2021-01
期刊: 2021 IEEE Symposium on Security and Privacy (SP)
影响因子: --
作者:
Subhajit Roy;Justin Hsu;Aws Albarghouthi
通讯作者: Subhajit Roy;Justin Hsu;Aws Albarghouthi
DP-Sniper:使用分类器黑盒发现差异隐私侵犯
DOI: --
发表时间: 2021
期刊: IEEE Symposium on Security and Privacy
影响因子: --
作者:
Benjamin Bichsel;Samuel Steffen;Ilija Bogunovic;Martin T. Vechev
通讯作者: Martin T. Vechev