arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.12124cs.LGcs.AI
收藏

SynQP:合成数据质量和隐私风险评估的框架与指标

SynQP: A Framework and Metrics for Evaluating the Quality and Privacy Risk of Synthetic Data

Computer Science University of Waterloo(计算机科学大学水力学院);Public Health Sciences University of Waterloo(公共卫生科学大学水力学院);Public Health Agency of Canada Government of Canada(加拿大公共卫生机构政府)

Bing Hu, Yixin Li, Asma Bahamyirou, Helen Chen

AI总结:

SynQP提出了一种用于评估合成数据质量和隐私风险的框架,通过模拟敏感数据进行基准测试,并引入新的身份披露风险指标以提高隐私评估的准确性。

摘要:

在健康应用中使用合成数据引发了隐私问题,但缺乏开放的隐私评估框架阻碍了其采用。主要挑战是缺乏可用于评估隐私风险的公开基准数据集,这归因于获取敏感数据的困难。为此,我们引入SynQP,一个用于评估合成数据生成(SDG)中隐私的开放框架,使用模拟敏感数据进行基准测试,确保原始数据保持保密。我们还强调了需要能够公平反映机器学习模型概率性质的隐私指标。作为演示,我们使用SynQP对CTGAN进行基准测试,并提出一个新的身份披露风险指标,该指标比现有方法提供了更准确的隐私风险估计。我们的工作提供了一种关键工具,以提高隐私评估的透明度和可靠性,从而在健康相关应用中更安全地使用合成数据。% 在我们的质量评估中,非隐私模型在机器学习效果上接近完美(≥0.97)。我们的隐私评估(表II)显示,差分隐私(DP)降低了身份披露风险(SD-IDR)和成员推断攻击风险(SD-MIA),所有DP增强的模型都低于0.09的监管阈值。代码可在https://github.com/CAN-SYNH/SynQP上获取。

英文摘要:

The use of synthetic data in health applications raises privacy concerns, yet the lack of open frameworks for privacy evaluations has slowed its adoption. A major challenge is the absence of accessible benchmark datasets for evaluating privacy risks, due to difficulties in acquiring sensitive data. To address this, we introduce SynQP, an open framework for benchmarking privacy in synthetic data generation (SDG) using simulated sensitive data, ensuring that original data remains confidential. We also highlight the need for privacy metrics that fairly account for the probabilistic nature of machine learning models. As a demonstration, we use SynQP to benchmark CTGAN and propose a new identity disclosure risk metric that offers a more accurate estimation of privacy risks compared to existing approaches. Our work provides a critical tool for improving the transparency and reliability of privacy evaluations, enabling safer use of synthetic data in health-related applications. % In our quality evaluations, non-private models achieved near-perfect machine-learning efficacy \(\ge0.97\). Our privacy assessments (Table II) reveal that DP consistently lowers both identity disclosure risk (SD-IDR) and membership-inference attack risk (SD-MIA), with all DP-augmented models staying below the 0.09 regulatory threshold. Code available at https://github.com/CAN-SYNH/SynQP

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。

↑