TC: Small: Integrating Privacy Preserving Biometric Templates and Efficient Indexing Methods

TC：小型：集成隐私保护生物识别模板和高效索引方法

• 批准号: 1115670
• 负责人: Venugopal Govindaraju
• 金额: $ 49.98万
• 依托单位: SUNY at Buffalo
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2011
• 资助国家: 美国
• 起止时间: 2011-09-01 至 2015-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1115670&HistoricalAwards=false
• 关键词: TC; Small; Integrating; Privacy; Preserving

Biometrics, such as fingerprints, provide a great tool for personalized authentication. While people are usually willing to submit their biometric information to government agencies, they are less likely to do so for commercial companies without a guarantee of privacy protection. This project will have significant societal impact by triggering wide acceptability of large-scale biometrics enabled applications.The primary technological hurdle faced by large scale biometric systems today is the ability to address two competing objectives: (1) provide fast matching of a biometric against a large database of stored biometric readings and (2) provide privacy of the biometrics in the database such that it can withstand malicious attacks. Existing solutions tackle either of the two problem but not both simultaneously.Tackling the two problems in an integrated fashion is non-trivial as any solution to conceal the biometric data to ensure privacy involves breaking down the structure inherent in the biometric template, thus making it extremely challenging to index the records efficiently. This project presents a unified approach by developing "cryptographically hidden" biometric templates which will lend themselves to fast searches. This effort will draw upon new research in the fields of biometrics, databases, and coding theory.

指纹等生物识别技术为个性化身份验证提供了一个很好的工具。虽然人们通常愿意将他们的生物识别信息提交给政府机构，但他们不太可能为没有隐私保护保证的商业公司这样做。该项目将引发大规模生物识别技术应用的广泛接受，从而产生重大的社会影响。当今大规模生物识别系统面临的主要技术障碍是解决两个相互竞争的目标的能力：（1）提供生物测定与存储的生物测定读数的大数据库的快速匹配，以及（2）提供数据库中的生物特征的隐私性，使得其能够经受住恶意攻击。现有的解决方案可以解决这两个问题中的任何一个，但不能同时解决这两个问题。以综合的方式解决这两个问题并不简单，因为任何隐藏生物特征数据以确保隐私的解决方案都涉及破坏生物特征模板中固有的结构，因此有效地索引记录是非常具有挑战性的。该项目提出了一个统一的方法，通过开发“加密隐藏”的生物特征模板，这将有助于快速搜索。这项工作将借鉴生物识别，数据库和编码理论领域的新研究。