# CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation

arXiv: https://arxiv.org/abs/2010.02338 · HTML: https://mlsanity.com/paper/2010.02338/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 30 of 44)

- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP](https://mlsanity.com/paper/2210.10683/) (2022)
- [Exploring the Universal Vulnerability of Prompt-based Learning Paradigm](https://mlsanity.com/paper/2204.05239/) (2022)
- [Are Vision Transformers Robust to Patch Perturbations?](https://mlsanity.com/paper/2111.10659/) (2021)
- [DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation](https://mlsanity.com/paper/2202.12350/) (2022)
- [Robustness of Learning from Task Instructions](https://mlsanity.com/paper/2212.03813/) (2022)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [Phrase-level Textual Adversarial Attack with Label Preservation](https://mlsanity.com/paper/2205.10710/) (2022)
- [Multi-granularity Textual Adversarial Attack with Behavior Cloning](https://mlsanity.com/paper/2109.04367/) (2021)
- [Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers](https://mlsanity.com/paper/2204.03503/) (2022)
- [Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text](https://mlsanity.com/paper/2506.07001/) (2025)
- [Flexible text generation for counterfactual fairness probing](https://mlsanity.com/paper/2206.13757/) (2022)
- [Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation](https://mlsanity.com/paper/2203.12709/) (2022)
- [Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2201.00768/) (2022)
- [ER-Test: Evaluating Explanation Regularization Methods for Language Models](https://mlsanity.com/paper/2205.12542/) (2022)
- [LEAP: Efficient and Automated Test Method for NLP Software](https://mlsanity.com/paper/2308.11284/) (2023)
- [Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets](https://mlsanity.com/paper/2311.08662/) (2023)
- [Masked Language Model Based Textual Adversarial Example Detection](https://mlsanity.com/paper/2304.08767/) (2023)
- [Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks](https://mlsanity.com/paper/2310.16955/) (2023)
- [ROIC-DM: Robust Text Inference and Classification via Diffusion Model](https://mlsanity.com/paper/2401.03514/) (2024)
- [Confidence Elicitation: A New Attack Vector for Large Language Models](https://mlsanity.com/paper/2502.04643/) (2025)
- [Low Resource Style Transfer via Domain Adaptive Meta Learning](https://mlsanity.com/paper/2205.12475/) (2022)
- [Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions](https://mlsanity.com/paper/2302.06801/) (2023)
- [TREATED:Towards Universal Defense against Textual Adversarial Attacks](https://mlsanity.com/paper/2109.06176/) (2021)
- [Consistent Text Categorization using Data Augmentation in e-Commerce](https://mlsanity.com/paper/2305.05402/) (2023)
- [From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework](https://mlsanity.com/paper/2305.18503/) (2023)
- [Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion](https://mlsanity.com/paper/2401.11373/) (2024)
- [PID Control-Based Self-Healing to Improve the Robustness of Large Language Models](https://mlsanity.com/paper/2404.00828/) (2024)
- [Automated Adversarial Discovery for Safety Classifiers](https://mlsanity.com/paper/2406.17104/) (2024)

## Abstract (arXiv)

NLP models are shown to suffer from robustness issues, i.e., a model's prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled Adversarial Text Generation (CAT-Gen) model that, given an input text, generates adversarial texts through controllable attributes that are known to be invariant to task labels. For example, in order to attack a model for sentiment classification over product reviews, we can use the product categories as the controllable attribute which would not change the sentiment of the reviews. Experiments on real-world NLP datasets demonstrate that our method can generate more diverse and fluent adversarial texts, compared to many existing adversarial text generation approaches. We further use our generated adversarial examples to improve models through adversarial training, and we demonstrate that our generated attacks are more robust against model re-training and different model architectures.