盲目的正义:加密敏感属性的公平
Blind Justice: Fairness with Encrypted Sensitive Attributes
摘要:
最近的工作已经探索了如何训练机器学习模型,这些模型不歧视由敏感属性(如性别或种族)确定的任何群体。为避免区别对待,不应考虑敏感属性。另一方面,为了避免不同的影响,必须检查敏感属性,例如,以便学习公平模型,或者检查给定模型是否公平。我们引入安全多方计算的方法,使我们能够避免这两种情况。通过加密敏感属性,我们展示了如何学习,检查基于结果的公平模型,或验证其输出并将其保留在帐户中,而无需用户泄露其敏感属性。
英文摘要:
Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes should not be considered. On the other hand, in order to avoid disparate impact, sensitive attributes must be examined, e.g., in order to learn a fair model, or to check if a given model is fair. We introduce methods from secure multi-party computation which allow us to avoid both. By encrypting sensitive attributes, we show how an outcome-based fair model may be learned, checked, or have its outputs verified and held to account, without users revealing their sensitive attributes.
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。