一句话：提出基于对抗采样的可扩展白盒公平性测试方法，高效搜索 DNN 的个体歧视实例。
深度神经网络（DNN）在许多任务上表现优异，但在具有社会影响的应用中，其公平性（即非歧视性）仍令人担忧。本文关注如何搜索 DNN 的个体歧视实例，以支撑公平性测试。作者提出一种可扩展的白盒方法，通过对抗采样进行搜索，仅依赖梯度计算和聚类等轻量级过程，因此比现有方法更易扩展。实验与当前最优方法比较，该方法对搜索空间的探索效果提升约 9 倍，生成的个体歧视实例数量提升约 25 倍，同时耗时仅为后者的二分之一到七分之一。
Although deep neural networks (DNNs) have demonstrated astonishing performance in many applications, there are still concerns on their dependability. One desirable property of DNN for applications with societal impact is fairness (i.e., non-discrimination). In this work, we propose a scalable approach for searching individual discriminatory instances of DNN. Compared with state-of-the-art methods, our approach only employs lightweight procedures like gradient computation and clustering, which makes it significantly more scalable than existing methods. Experimental results show that our approach explores the search space more effectively (9 times) and generates much more individual discriminatory instances (25 times) using much less time (half to 1/7).
@inproceedings{paperbot5648,
title = {White-box fairness testing through adversarial sampling},
author = {Peixin Zhang and Jingyi Wang and Jun Sun and Guoliang Dong and Xinyu Wang and Xingen Wang and Jin Song Dong and Ting Dai},
booktitle = {ICSE},
year = {2020},
doi = {10.1145/3377811.3380331}
}