论文标题
西班牙小吃：用于对抗性隐私审核合成数据的工具箱
TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
论文作者
论文摘要
大规模收集的个人数据有望改善决策和加速创新。但是，共享和使用此类数据引起了严重的隐私问题。一个有希望的解决方案是生成合成数据，人工记录要共享而不是实际数据。由于综合记录与真实人没有联系，因此直觉上可以防止经典的重新识别攻击。但是，这不足以保护隐私。我们在这里提出小吃，这是一种攻击工具箱，可在各种方案下评估合成数据隐私。这些攻击包括对先前作品和新颖攻击的概括。我们还介绍了一个通用框架，以在几个示例中推理有关合成数据的隐私威胁并展示小吃的一般框架。
Personal data collected at scale promises to improve decision-making and accelerate innovation. However, sharing and using such data raises serious privacy concerns. A promising solution is to produce synthetic data, artificial records to share instead of real data. Since synthetic records are not linked to real persons, this intuitively prevents classical re-identification attacks. However, this is insufficient to protect privacy. We here present TAPAS, a toolbox of attacks to evaluate synthetic data privacy under a wide range of scenarios. These attacks include generalizations of prior works and novel attacks. We also introduce a general framework for reasoning about privacy threats to synthetic data and showcase TAPAS on several examples.
