# Towards a Robust Deep Neural Network in Texts: A Survey

arXiv: https://arxiv.org/abs/1902.07285 · HTML: https://mlsanity.com/paper/1902.07285/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [On Robustness of Neural Semantic Parsers](https://mlsanity.com/paper/2102.01563/) (2021)
- [A Differentiable Language Model Adversarial Attack on Text Classifiers](https://mlsanity.com/paper/2107.11275/) (2021)
- [On the Robustness of Explanations of Deep Neural Network Models: A Survey](https://mlsanity.com/paper/2211.04780/) (2022)
- [Tribrid: Stance Classification with Neural Inconsistency Detection](https://mlsanity.com/paper/2109.06508/) (2021)
- [Machine Translation Models Stand Strong in the Face of Adversarial Attacks](https://mlsanity.com/paper/2309.06527/) (2023)

## Abstract (arXiv)

Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are vulnerable to adversarial examples, which cause erroneous predictions by adding imperceptible perturbations into legitimate inputs. Recently, studies have revealed adversarial examples in the text domain, which could effectively evade various DNN-based text analyzers and further bring the threats of the proliferation of disinformation. In this paper, we give a comprehensive survey on the existing studies of adversarial techniques for generating adversarial texts written by both English and Chinese characters and the corresponding defense methods. More importantly, we hope that our work could inspire future studies to develop more robust DNN-based text analyzers against known and unknown adversarial techniques. We classify the existing adversarial techniques for crafting adversarial texts based on the perturbation units, helping to better understand the generation of adversarial texts and build robust models for defense. In presenting the taxonomy of adversarial attacks and defenses in the text domain, we introduce the adversarial techniques from the perspective of different NLP tasks. Finally, we discuss the existing challenges of adversarial attacks and defenses in texts and present the future research directions in this emerging and challenging field.