Data modification, either via additional training datasets, data augmentation, debiasing, and dataset filtering, has been proposed as an effective solution for generalizing to out-of-domain (OOD) inputs, in both natural language processing and computer vision literature. However, the effect of data modification on adversarial robustness remains unclear. In this work, we conduct a comprehensive study of common data modification strategies and evaluate not only their in-domain and OOD performance, but also their adversarial robustness (AR). We also present results on a two-dimensional synthetic dataset to visualize the effect of each method on the training distribution. This work serves as an empirical study towards understanding the relationship between generalizing to unseen domains and defending against adversarial perturbations. Our findings suggest that more data (either via additional datasets or data augmentation) benefits both OOD accuracy and AR. However, data filtering (previously shown to improve OOD accuracy on natural language inference) hurts OOD accuracy on other tasks such as question answering and image classification. We provide insights from our experiments to inform future work in this direction.

本文通过研究数据修正、数据增强、去偏、数据过滤等方法对模型泛化到未知领域和对抗鲁棒性的影响，发现数据的增加（通过增加数据集或数据增强）能够提高模型在未知领域下的准确性和抗干扰能力，而数据过滤则会减少针对特定任务的准确性。

广泛但不健壮？比较数据修改方法对领域外泛化和对抗鲁棒性的影响