mlsanityData to 7 Oct 2026

A Survey of Adversarial Defences and Robustness in NLP

arXiv 2203.06414 ↗First posted 12 Mar 2022cs.CLcited by 22

Not on the map. Why?

Abstract (arXiv)

In the past few years, it has become increasingly evident that deep neural networks are not resilient enough to withstand adversarial perturbations in input data, leaving them vulnerable to attack. Various authors have proposed strong adversarial attacks for computer vision and Natural Language Processing (NLP) tasks. As a response, many defense mechanisms have also been proposed to prevent these networks from failing. The significance of defending neural networks against adversarial attacks lies in ensuring that the model's predictions remain unchanged even if the input data is perturbed. Several methods for adversarial defense in NLP have been proposed, catering to different NLP tasks such as text classification, named entity recognition, and natural language inference. Some of these methods not only defend neural networks against adversarial attacks but also act as a regularization mechanism during training, saving the model from overfitting. This survey aims to review the various methods proposed for adversarial defenses in NLP over the past few years by introducing a novel taxonomy. The survey also highlights the fragility of advanced deep neural networks in NLP and the challenges involved in defending them.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 116 of its 173 references that are in the map. First posted on arXiv 12 Mar 2022.

Builds on

116 of 173 references.

References · 116

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  3. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  4. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  5. 2015Teaching Machines to Read and Comprehendcited by 1,039
  6. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  7. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  8. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  9. 2019Adversarial Training for Free!cited by 638
  10. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  11. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  12. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
38 more
  1. 2018Generating Natural Language Adversarial Examplescited by 422
  2. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 395
  3. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
  4. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  5. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  6. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  7. 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
  8. 2018Certified Defenses against Adversarial Examplescited by 305
  9. 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 304
  10. 2017Certified Defenses for Data Poisoning Attackscited by 288
  11. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
  12. 2018A Survey on Deep Learning for Named Entity Recognitioncited by 281
  13. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  14. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
  15. 2018Adversarial Attacks and Defences: A Surveycited by 259
  16. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  17. 2017Generating Natural Adversarial Examplescited by 182
  18. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
  19. 2019Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attackcited by 176
  20. 2019Certified Robustness to Adversarial Word Substitutionscited by 164
  21. 2019Text Classification Algorithms: A Surveycited by 163
  22. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 162
  23. 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
  24. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  25. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  26. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 138
  27. 2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 133
  28. 2019A Survey on Recent Advances in Named Entity Recognition from Deep Learning modelscited by 117
  29. 2017Natural Language Processing: State of The Art, Current Trends and Challengescited by 114
  30. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  31. 2020Adversarial Training for Large Neural Language Modelscited by 109
  32. 2017Deep Text Classification Can be Fooledcited by 105
  33. 2019Robust Neural Machine Translation with Doubly Adversarial Inputscited by 105
  34. 2017Deceiving Google's Perspective API Built for Detecting Toxic Commentscited by 99
  35. 2019Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Surveycited by 93
  36. 2020InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspectivecited by 92
  37. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  38. 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87

50 most cited of 116 All 116 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 7; 2025: 1; 2026: 1.

22 papers.

Sort:

By area:

  1. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  2. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  3. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  4. 2023In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPTcited by 35
  5. 2023Towards Explainable Evaluation Metrics for Machine Translationcited by 15
  6. 2023Randomized Smoothing with Masked Inference for Adversarially Robust Text Classificationscited by 11
  7. 2024Enhancing Trust in LLMs: Algorithms for Comparing and Interpreting LLMscited by 9
  8. 2023TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classificationcited by 8
  9. 2024Adversarial Text Purification: A Large Language Model Approach for Defensecited by 8
  10. 2024Improving Black-box Robustness with In-Context Rewritingcited by 8
  11. 2023DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimizationcited by 7
  12. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
10 more
  1. 2024Extreme Miscalibration and the Illusion of Adversarial Robustnesscited by 4
  2. 2024Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learningcited by 4
  3. 2023Data Augmentation for Neural NLPcited by 2
  4. 2023A Multilingual Evaluation of NER Robustness to Adversarial Inputscited by 2
  5. 2023Sample Attackability in Natural Language Adversarial Attackscited by 2
  6. 2024MaskPure: Improving Defense Against Text Adversaries with Stochastic Purificationcited by 2
  7. 2024Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarialscited by 1
  8. 2025Attacks and Defenses Against LLM Fingerprintingcited by 1
  9. 2023Adversarial training for tabular data with attack propagationcited by 0
  10. 2026Evaluation of Adversarial Robustness in Arabic Language Modelscited by 0