mlsanityData to 7 Oct 2026

TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

arXiv 2005.05909 ↗First posted 29 Apr 2020cs.CL cs.AI cs.LGcited by 45

Not on the map. Why?

Abstract (arXiv)

While there has been substantial research using adversarial attacks to analyze NLP models, each attack is implemented in its own code repository. It remains challenging to develop NLP attacks and utilize them to improve model performance. This paper introduces TextAttack, a Python framework for adversarial attacks, data augmentation, and adversarial training in NLP. TextAttack builds attacks from four components: a goal function, a set of constraints, a transformation, and a search method. TextAttack's modular design enables researchers to easily construct attacks from combinations of novel and existing components. TextAttack provides implementations of 16 adversarial attacks from the literature and supports a variety of models and datasets, including BERT and other transformers, and all GLUE tasks. TextAttack also includes data augmentation and adversarial training modules for using components of adversarial attacks to improve model accuracy and robustness. TextAttack is democratizing NLP: anyone can try data augmentation and adversarial training on any model or dataset, with just a few lines of code. Code and tutorials are available at https://github.com/QData/TextAttack.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 7; 2023: 11; 2024: 7; 2025: 5; 2026: 1.

45 papers.

Sort:

By area:

  1. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  2. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  3. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 107
  4. 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
  5. 2021Towards Improving Adversarial Training of NLP Modelscited by 79
  6. 2023Robust Multi-bit Natural Language Watermarking through Invariant Featurescited by 76
  7. 2021Grey-box Adversarial Attack And Defence For Sentiment Classificationcited by 28
  8. 2025Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Modelscited by 23
  9. 2024Benchmarking Large Multimodal Models against Common Corruptionscited by 22
  10. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Trainingcited by 20
  11. 2024Prompt Perturbation in Retrieval-Augmented Generation based Large Language Modelscited by 17
  12. 2024Towards Building a Robust Toxicity Predictorcited by 14
33 more
  1. 2021Token-Modification Adversarial Attacks for Natural Language Processing: A Surveycited by 12
  2. 2024Visual Robustness Benchmark for Visual Question Answering (VQA)cited by 12
  3. 2022An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networkscited by 11
  4. 2022Designing Robust Transformers using Robust Kernel Density Estimationcited by 11
  5. 2022Self-supervised Context-aware Style Representation for Expressive Speech Synthesiscited by 10
  6. 2021A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Trackingcited by 9
  7. 2022A Simple, Yet Effective Approach to Finding Biases in Code Generationcited by 8
  8. 2023Verifying the Robustness of Automatic Credibility Assessmentcited by 8
  9. 2023Shilling Black-box Review-based Recommender Systems through Fake Review Generationcited by 8
  10. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  11. 2024Enhancing Adversarial Attacks through Chain of Thoughtcited by 8
  12. 2023CitySpec with Shield: A Secure Intelligent Assistant for Requirement Formalizationcited by 7
  13. 2021Personalized Benchmarking with the Ludwig Benchmarking Toolkitcited by 6
  14. 2022Interactive Machine Learning: A State of the Art Reviewcited by 6
  15. 2024VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoningcited by 6
  16. 2021Semantic-Preserving Adversarial Text Attackscited by 5
  17. 2022Text Transformations in Contrastive Self-Supervised Learning: A Reviewcited by 5
  18. 2021Back-Translated Task Adaptive Pretraining: Improving Accuracy and Robustness on Text Classificationcited by 3
  19. 2023Expanding Scope: Adapting English Adversarial Attacks to Chinesecited by 3
  20. 2025Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classificationscited by 2
  21. 2021Robustness Evaluation of Transformer-based Form Field Extractors via Form Attackscited by 1
  22. 2025Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Modelscited by 1
  23. 2025Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systemscited by 1
  24. 2021TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processingcited by 0
  25. 2021Robustness Tests of NLP Machine Learning Models: Search and Semantically Replacecited by 0
  26. 2021CABACE: Injecting Character Sequence Information and Domain Knowledge for Enhanced Acronym and Long-Form Extractioncited by 0
  27. 2022A Simple Yet Efficient Method for Adversarial Word-Substitute Attackcited by 0
  28. 2023Knowledge-Based Counterfactual Queries for Visual Question Answeringcited by 0
  29. 2023CGDTest: A Constrained Gradient Descent Algorithm for Testing Neural Networkscited by 0
  30. 2023A Melting Pot of Evolution and Learningcited by 0
  31. 2023DEFTri: A Few-Shot Label Fused Contextual Representation Learning For Product Defect Triage in e-Commercecited by 0
  32. 2025GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Researchcited by 0
  33. 2026Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Textcited by 0