mlsanityData to 7 Oct 2026

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

arXiv 2010.02338 ↗First posted 5 Oct 2020cs.CLcited by 43

Not on the map. Why?

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.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 13; 2023: 8; 2024: 9; 2025: 6; 2026: 1.

43 papers.

Sort:

By area:

  1. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  2. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  3. 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
  4. 2022Exploring the Universal Vulnerability of Prompt-based Learning Paradigmcited by 56
  5. 2021Are Vision Transformers Robust to Patch Perturbations?cited by 39
  6. 2022DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptationcited by 36
  7. 2022Robustness of Learning from Task Instructionscited by 34
  8. 2022Phrase-level Textual Adversarial Attack with Label Preservationcited by 23
  9. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  10. 2021Multi-granularity Textual Adversarial Attack with Behavior Cloningcited by 21
  11. 2022Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformerscited by 20
  12. 2025Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Textcited by 16
31 more
  1. 2022Flexible text generation for counterfactual fairness probingcited by 13
  2. 2022Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretationcited by 12
  3. 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 9
  4. 2022ER-Test: Evaluating Explanation Regularization Methods for Language Modelscited by 6
  5. 2023LEAP: Efficient and Automated Test Method for NLP Softwarecited by 6
  6. 2023Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Setscited by 6
  7. 2023Masked Language Model Based Textual Adversarial Example Detectioncited by 5
  8. 2023Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attackscited by 5
  9. 2024ROIC-DM: Robust Text Inference and Classification via Diffusion Modelcited by 5
  10. 2022Low Resource Style Transfer via Domain Adaptive Meta Learningcited by 4
  11. 2025Confidence Elicitation: A New Attack Vector for Large Language Modelscited by 4
  12. 2023Consistent Text Categorization using Data Augmentation in e-Commercecited by 3
  13. 2023From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Frameworkcited by 3
  14. 2024Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortioncited by 3
  15. 2024PID Control-Based Self-Healing to Improve the Robustness of Large Language Modelscited by 3
  16. 2024Automated Adversarial Discovery for Safety Classifierscited by 3
  17. 2021TREATED:Towards Universal Defense against Textual Adversarial Attackscited by 2
  18. 2022Plug and Play Counterfactual Text Generation for Model Robustnesscited by 2
  19. 2024Enhance Robustness of Language Models Against Variation Attack through Graph Integrationcited by 2
  20. 2024CERT-ED: Certifiably Robust Text Classification for Edit Distancecited by 2
  21. 2025Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removalcited by 2
  22. 2023Improving Classifier Robustness through Active Generation of Pairwise Counterfactualscited by 1
  23. 2024Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signalscited by 1
  24. 2025Exploring Robustness of LLMs to Paraphrasing Based on Sociodemographic Factorscited by 1
  25. 2025Model Hemorrhage and the Robustness Limits of Large Language Modelscited by 1
  26. 2021SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Textcited by 0
  27. 2023SenTest: Evaluating Robustness of Sentence Encoderscited by 0
  28. 2024Towards Robust Domain Generation Algorithm Classificationcited by 0
  29. 2024LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Modelscited by 0
  30. 2025Coordinated Robustness Evaluation Framework for Vision-Language Modelscited by 0
  31. 2026Applications of the Transformer Architecture in AI-Assisted English Reading Comprehensioncited by 0