arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07441cs.CRcs.PL
收藏

DPGen:用于差分隐私的自动程序合成

DPGen: Automated Program Synthesis for Differential Privacy

Yuxin Wang, Zeyu Ding, Yingtai Xiao, Daniel Kifer, Danfeng Zhang

摘要:

差分隐私已经成为以隐私保护方式发布数据的事实标准。创建差异私有算法的过程通常从无噪声(非私有)算法开始。然后,设计者决定在哪里添加噪声,以及添加多少噪声。这可能是一个不平凡的过程--如果不仔细做,算法可能会违反差分隐私或具有低效用。在本文中,我们提出了DPGen,一个程序合成器,需要在非私有代码(没有任何噪声),并自动合成其差分私有版本(仔细校准的噪声)。在引擎盖下,DPGen使用新的算法自动生成一个草图程序,其中包含噪声的候选位置,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,自适应地处理查询,直到指定的隐私预算耗尽。在标准基准测试中进行评估时,DPGen能够在120秒内生成优化简单效用函数的差异化私有机制。它也足够强大,可以合成自适应隐私机制。

英文摘要:

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.

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。

↑