Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning
This work addresses the problem of improving adversarial robustness for pretrained language models in text classification, which is an incremental improvement over existing adversarial data augmentation methods.
Pretrained language models (PLMs) are vulnerable to adversarial attacks. This paper proposes Adversarial and Mixup Data Augmentation (AMDA), which interpolates representations of training samples to create more diverse virtual samples, significantly improving robustness for BERT and RoBERTa in text classification under two strong adversarial attacks while mitigating clean data performance degradation.
Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial attacks by adding textual adversarial examples during training. However, the number of adversarial examples for text augmentation is still extremely insufficient due to the exponentially large attack search space. In this work, we propose a simple and effective method to cover a much larger proportion of the attack search space, called Adversarial and Mixup Data Augmentation (AMDA). Specifically, AMDA linearly interpolates the representations of pairs of training samples to form new virtual samples, which are more abundant and diverse than the discrete text adversarial examples in conventional ADA. Moreover, to fairly evaluate the robustness of different models, we adopt a challenging evaluation setup, which generates a new set of adversarial examples targeting each model. In text classification experiments of BERT and RoBERTa, AMDA achieves significant robustness gains under two strong adversarial attacks and alleviates the performance degradation of ADA on the clean data. Our code is available at: https://github.com/thunlp/MixADA .