A Survey: Towards a Robust Deep Neural Network in Text Domain

Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing). However, researches have shown that DNN models are vulnerable to adversarial examples, which cause incorrect predictions by adding imperceptible perturbations into normal inputs. Studies on adversarial examples in image domain have been well investigated, but in texts the research is not enough, let alone a comprehensive survey in this field. In this paper, we aim at presenting a comprehensive understanding of adversarial attacks and corresponding mitigation strategies in texts. Specifically, we first give a taxonomy of adversarial attacks and defenses in texts from the perspective of different natural language processing (NLP) tasks, and then introduce how to build a robust DNN model via testing and verification. Finally, we discuss the existing challenges of adversarial attacks and defenses in texts and present the future research directions in this emerging field.