arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.07239cs.CR
收藏

密钥协商与计算差分隐私的分离性研究

Separating Key Agreement and Computational Differential Privacy

Vipul Arora, Eldon Chung, Zeyong Li, Thomas Tan

AI总结:

本研究证明仅黑盒调用密钥协商的高效计算差分隐私协议必满足信息论差分隐私,结合已有下界表明密钥协商严格弱于内积计算的计算差分隐私,解答了相关开放问题。

摘要:

两方差分隐私允许互不信任的两方共同对其数据开展联合分析,同时保障个体级隐私。我们证明:任何仅以黑盒方式调用密钥协商(无更强原语)的高效计算差分隐私协议,同时也是高效的信息论差分隐私协议。换言之,高效密钥协商协议的存在性不足以支撑高效计算差分隐私协议的构建。该结果推动解答了Vadhan提出的关于计算差分隐私所需最小计算假设的开放问题。结合McGregor、Mironov、Pitassi、Reingold、Talwar与Vadhan在[FOCS'10]中提出的信息论下界,我们证明:针对n比特数据计算汉明距离(等价于整数域内积)、加性误差低于O(√n/(e^ε log n))的高效计算差分隐私协议,不存在到密钥协商的完全黑盒归约。该结果补充了Haitner、Mazor、Silbak与Tsfadia在[STOC'22]中提出的结论——汉明距离计算可推导出密钥协商。我们最终得出:在内积计算场景下,密钥协商严格弱于计算差分隐私,由此解答了上述学者提出的“密钥协商是否足够”的开放问题。

英文摘要:

Two party differential privacy allows two parties who do not trust each other, to come together and perform a joint analysis on their data whilst maintaining individual-level privacy. We show that any efficient, computationally differentially private protocol that has black-box access to key agreement (and nothing stronger), is also an efficient, information-theoretically differentially private protocol. In other words, the existence of efficient key agreement protocols is insufficient for efficient, computationally differentially private protocols. In doing so, we make progress in answering an open question posed by Vadhan about the minimal computational assumption needed for computational differential privacy. Combined with the information-theoretic lower bound due to McGregor, Mironov, Pitassi, Reingold, Talwar, and Vadhan in [FOCS'10], we show that there is no fully black-box reduction from efficient, computationally differentially private protocols for computing the Hamming distance (or equivalently inner product over the integers) on $n$ bits, with additive error lower than $O\left(\frac{\sqrt{n}}{e^ε\log(n)}\right)$, to key agreement. This complements the result by Haitner, Mazor, Silbak, and Tsfadia in [STOC'22], which showed that computing the Hamming distance implies key agreement. We conclude that key agreement is \emph{strictly} weaker than computational differential privacy for computing the inner product, thereby answering their open question on whether key agreement is sufficient.

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。

↑