# Adversarial Attacks and Defense on Texts: A Survey

arXiv: https://arxiv.org/abs/2005.14108 · HTML: https://mlsanity.com/paper/2005.14108/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2020.

## Built on by (most cited first, 12 of 12)

- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview](https://mlsanity.com/paper/2206.07438/) (2022)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [Certified Robustness to Programmable Transformations in LSTMs](https://mlsanity.com/paper/2102.07818/) (2021)
- [BERT Rankers are Brittle: a Study using Adversarial Document Perturbations](https://mlsanity.com/paper/2206.11724/) (2022)
- [On the Robustness of Explanations of Deep Neural Network Models: A Survey](https://mlsanity.com/paper/2211.04780/) (2022)
- [Experiments with adversarial attacks on text genres](https://mlsanity.com/paper/2107.02246/) (2021)
- [A Comprehensive Analysis of Adversarial Attacks against Spam Filters](https://mlsanity.com/paper/2505.03831/) (2025)
- [Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.20859/) (2025)
- [From text to multimodal: a survey of adversarial example generation in question answering systems](https://mlsanity.com/paper/2312.16156/) (2023)
- [ARAFA: An LLM-Generated Arabic Fact-Checking Dataset](https://mlsanity.com/paper/2609.25833/) (2026)

## Abstract (arXiv)

Deep learning models have been used widely for various purposes in recent years in object recognition, self-driving cars, face recognition, speech recognition, sentiment analysis, and many others. However, in recent years it has been shown that these models possess weakness to noises which force the model to misclassify. This issue has been studied profoundly in the image and audio domain. Very little has been studied on this issue concerning textual data. Even less survey on this topic has been performed to understand different types of attacks and defense techniques. In this manuscript, we accumulated and analyzed different attacking techniques and various defense models to provide a more comprehensive idea. Later we point out some of the interesting findings of all papers and challenges that need to be overcome to move forward in this field.