Privacy-respecting collaborative data analysis

尊重隐私的协作数据分析

• 批准号: 531191-2018
• 负责人: Kerschbaum, Florian
• 金额: $ 12.06万
• 依托单位: University of Waterloo
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=697719
• 关键词: Privacy; respecting; collaborative; data; analysis

The digital economy is driven by (big) data. The ubiquitous collection of data by almost all stakeholders is exploited for their economic benefit. For example, banks may provide better services to their customers by the analysis of their cell phone data. However that data may not only be used for social benefit, but also unwanted or even prohibited uses, e.g. violating one's privacy. Hence, it is necessary by law and for social acceptability to protect the privacy of individuals to the utmost possible extent and prevent unwanted inferences while still enabling the use of the data for the social or economic benefit. This challenge is exacerbated, since the data may be distributed among several entities each of whom has been entrusted with the data for a specific purpose. Differential privacy can be used to protect an individual against inferences from the result of a data analysis. Cryptography can protect privacy during data storage and processing, e.g. using homomorphic or functional encryption and secure multi-party computation. In this proposal we look beyond the optimization of a single technology, but at the appropriate - often combined - use of those two technologies for important application in privacy-preserving data analysis. We evaluate the security and efficiency of the proposed solutions in comparison to existing approaches aiming at a privacy level acceptable for data protection in the financial industry.

数字经济是由大数据驱动的。几乎所有利益相关者无处不在的数据收集都被用于其经济利益。例如，银行可以通过分析客户的手机数据来为客户提供更好的服务。然而，这些数据不仅可能用于社会利益，而且可能用于不想要的甚至是禁止的用途，例如侵犯个人隐私。因此，法律和社会的可接受性都必须尽可能保护个人隐私，防止不必要的推论，同时仍然能够将数据用于社会或经济利益。由于数据可能分布在多个实体之间，每个实体都被委托用于特定目的，因此这一挑战变得更加严峻。 差异隐私可以用来保护个人免受数据分析结果的推断。密码学可以在数据存储和处理期间保护隐私，例如使用同态或函数加密和安全多方计算。在本提案中，我们不仅关注单一技术的优化，而且关注这两种技术在隐私保护数据分析中的重要应用的适当（通常是组合）使用。我们评估的安全性和效率相比，现有的方法，旨在在金融行业的数据保护可接受的隐私级别的建议的解决方案。