间接影响的审计黑箱模型
Auditing Black-box Models for Indirect Influence
摘要：
数据训练的预测模型得到了广泛的使用，但在大多数情况下，它们被用作输出预测或分数的黑盒。因此，很难更深入地了解模型行为，特别是不同的特征如何影响模型预测。在解释复杂模型的行为时，或者断言某些有问题的属性（如种族或性别）不会过度影响决策时，这一点很重要。在本文中，我们提出了一种用于审计黑盒模型的技术，该技术可以让我们研究现有模型在多大程度上利用了数据集中的特定功能，而不知道模型如何工作。我们的工作重点是间接影响的问题：一些特征如何通过其他相关特征间接影响结果。因此，即使在进一步直接检查模型时，模型根本没有引用属性的情况下，我们也可以发现属性的影响。我们的方法不需要重新训练黑盒模型。如果（例如）模型只能通过API访问，这一点很重要，并且将我们的工作与其他研究特征影响的方法（如特征选择）进行了对比。我们使用各种公开的数据集和模型为我们的程序的有效性提供了实验证据。我们还使用可解释学习和特征选择技术以及其他黑盒审计程序来验证我们的程序。
英文摘要：
Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting the behavior of complex models, or asserting that certain problematic attributes (like race or gender) are not unduly influencing decisions. In this paper, we present a technique for auditing black-box models, which lets us study the extent to which existing models take advantage of particular features in the dataset, without knowing how the models work. Our work focuses on the problem of indirect influence: how some features might indirectly influence outcomes via other, related features. As a result, we can find attribute influences even in cases where, upon further direct examination of the model, the attribute is not referred to by the model at all. Our approach does not require the black-box model to be retrained. This is important if (for example) the model is only accessible via an API, and contrasts our work with other methods that investigate feature influence like feature selection. We present experimental evidence for the effectiveness of our procedure using a variety of publicly available datasets and models. We also validate our procedure using techniques from interpretable learning and feature selection, as well as against other black-box auditing procedures.
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。
