权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

SaTC: CORE: Large: Collaborative: Accountable Information Use: Privacy and Fairness in Decision-Making Systems

SaTC：核心：大型：协作：负责任的信息使用：决策系统中的隐私和公平

基本信息

批准号：
1704845
负责人：
Matthew Fredrikson
金额：
$ 165万
依托单位：
Carnegie-Mellon University
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-06-01 至 2024-05-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1704845&HistoricalAwards=false
关键词：
SaTC CORE Large Collaborative Accountable

项目摘要

Increasingly, decisions and actions affecting people's lives are determined by automated systems processing personal data. Excitement about these systems has been accompanied by serious concerns about their opacity and the threats that they pose to privacy, fairness, and other values. Recognizing these concerns, the investigators seek to make real-world automated decision-making systems accountable for privacy and fairness by enabling them to detect and explain violations of these values. The technical work is informed by, and applied to, online advertising, healthcare, and criminal justice, in collaboration with and as advised by domain experts. Addressing privacy and fairness in decision systems requires providing formal definitional frameworks and practical system designs. The investigators provide new notions of privacy and fairness that deal with both protected information itself and proxies for it, while handling context-dependent, normative definitions of violations. A fundamental tension they address pits the access given to auditors of a system against the system owners' intellectual property protections and the confidentiality of the personal data used by the system. The investigators decompose such auditing into stages, where the level of access granted to an auditor is increased when potential (but not explainable) violations of privacy or fairness are detected. Workshops and public releases of code and data amplify the investigators' interactions with policy makers and other stakeholders. Their partnerships with outreach organizations encourage diversity.

影响人们生活的决策和行动越来越多地由处理个人数据的自动化系统决定。对这些系统的兴奋伴随着对其不透明性及其对隐私、公平和其他价值观构成的威胁的严重担忧。认识到这些担忧，研究人员试图做出真实世界的自动化决策-通过使系统能够检测和解释违反这些价值观的行为，使系统对隐私和公平负责。技术工作由在线广告、医疗保健和刑事司法提供信息并应用于这些领域，与领域专家合作，并根据领域专家的建议。解决决策系统中的隐私和公平性问题需要提供正式的定义框架和实用的系统设计。研究人员提供了隐私和公平性的新概念，既处理受保护的信息本身，也处理受保护的信息的代理，同时处理上下文相关的，违规行为的规范性定义。他们解决的一个基本矛盾是，系统审计员的访问权限与系统所有者的知识产权保护和系统使用的个人数据的机密性相冲突。调查人员将这种审计分解为阶段，当检测到潜在的（但无法解释的）侵犯隐私或公平性的行为时，增加授予审计员的访问级别。研讨会和代码和数据的公开发布扩大了调查人员与政策制定者和其他利益相关者的互动。他们与外联组织的伙伴关系鼓励多样性。

项目成果

期刊论文数量（21）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Machine Learning Models that Remember Too Much

DOI：
10.1145/3133956.3134077
发表时间：
2017-09
期刊：
Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security
影响因子：
0
作者：
Congzheng Song;Thomas Ristenpart;Vitaly Shmatikov
通讯作者：
Congzheng Song;Thomas Ristenpart;Vitaly Shmatikov

Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness