When deploying artificial intelligence (AI) in the real world, being able to trust the operation of the AI by characterizing how it performs is an ever-present and important topic. An important and still largely unexplored task in this characterization is determining major factors within the real world that affect the AI's behavior, such as weather conditions or lighting, and either a) being able to give justification for why it may have failed or b) eliminating the influence the factor has. Determining these sensitive factors heavily relies on collected data that is diverse enough to cover numerous combinations of these factors, which becomes more onerous when having many potential sensitive factors or operating in complex environments. This paper investigates methods that discover and separate out individual semantic sensitive factors from a given dataset to conduct this characterization as well as addressing mitigation of these factors' sensitivity. We also broaden remediation of fairness, which normally only addresses socially relevant factors, and widen it to deal with the desensitization of AI with regard to all possible aspects of variation in the domain. The proposed methods which discover these major factors reduce the potentially onerous demands of collecting a sufficiently diverse dataset. In experiments using the road sign (GTSRB) and facial imagery (CelebA) datasets, we show the promise of using this scheme to perform this characterization and remediation and demonstrate that our approach outperforms state of the art approaches.

中文翻译：

---

概括公平性：未知敏感属性的发现和缓解

在现实世界中部署人工智能 (AI) 时，能够通过表征其执行方式来信任 AI 的操作是一个永远存在且重要的话题。在此表征中，一项重要且尚未探索的任务是确定现实世界中影响 AI 行为的主要因素，例如天气条件或光照，并且 a) 能够为其可能失败的原因提供理由或 b) 消除因素的影响。确定这些敏感因素在很大程度上依赖于收集的数据，这些数据足够多样化以涵盖这些因素的多种组合，当有许多潜在的敏感因素或在复杂环境中运行时，这变得更加繁重。本文研究了从给定数据集中发现和分离出单个语义敏感因素以进行这种表征以及解决这些因素敏感性的缓解的方法。我们还扩大了公平的补救措施，这通常只解决与社会相关的因素，并将其扩大到处理人工智能在该领域所有可能的变化方面的脱敏。发现这些主要因素的拟议方法减少了收集足够多样化数据集的潜在繁重需求。在使用道路标志 (GTSRB) 和面部图像 (CelebA) 数据集的实验中，我们展示了使用该方案进行这种表征和修复的前景，并证明我们的方法优于最先进的方法。