mlsanityData to 7 Oct 2026

Grey-box Adversarial Attack And Defence For Sentiment Classification

arXiv 2103.11576 ↗First posted 22 Mar 2021cs.LG cs.AI cs.CLcited by 28

Not on the map. Why?

Abstract (arXiv)

We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 22 Mar 2021.

Builds on

24 of 32 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  8. 2019When Does Label Smoothing Help?cited by 985
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  10. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  11. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  12. 2018Universal Sentence Encodercited by 485
12 more
  1. 2018Generating Natural Language Adversarial Examplescited by 422
  2. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  3. 2019Certified Robustness to Adversarial Word Substitutionscited by 164
  4. 2016Counter-fitting Word Vectors to Linguistic Constraintscited by 138
  5. 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
  6. 2020Reevaluating Adversarial Examples in Natural Languagecited by 83
  7. 2018Did you hear that? Adversarial Examples Against Automatic Speech Recognitioncited by 48
  8. 2020TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLPcited by 45
  9. 2020How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Contextcited by 26
  10. 2020Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemblecited by 26
  11. 2018Adversarial Texts with Gradient Methodscited by 14
  12. 2020Elephant in the Room: An Evaluation Framework for Assessing Adversarial Examples in NLPcited by 7

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 9; 2023: 6; 2024: 10; 2025: 2.

28 papers.

Sort:

By area:

  1. 2022Federated Learning for Privacy Preservation in Smart Healthcare Systems: A Comprehensive Surveycited by 31
  2. 2022Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitutioncited by 28
  3. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  4. 2022On Robust Prefix-Tuning for Text Classificationcited by 15
  5. 2022A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictionscited by 15
  6. 2022Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detectioncited by 13
  7. 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 9
  8. 2023LEAP: Efficient and Automated Test Method for NLP Softwarecited by 6
  9. 2022Rethinking Textual Adversarial Defense for Pre-trained Language Modelscited by 5
  10. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  11. 2024Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Modelscited by 4
  12. 2024On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoningcited by 4
16 more
  1. 2024Arabic Synonym BERT-based Adversarial Examples for Text Classificationcited by 3
  2. 2024PID Control-Based Self-Healing to Improve the Robustness of Large Language Modelscited by 3
  3. 2021Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Modelscited by 2
  4. 2023OMG-ATTACK: Self-Supervised On-Manifold Generation of Transferable Evasion Attackscited by 2
  5. 2024On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMscited by 2
  6. 2025NLP Security and Ethics, in the Wildcited by 2
  7. 2025Text Adversarial Attacks with Dynamic Outputscited by 2
  8. 2023Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classificationcited by 1
  9. 2024Exploiting Class Probabilities for Black-box Sentence-level Attackscited by 1
  10. 2024DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoisingcited by 1
  11. 2022Robust DNN Surrogate Models with Uncertainty Quantification via Adversarial Trainingcited by 0
  12. 2023SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classificationcited by 0
  13. 2023SenTest: Evaluating Robustness of Sentence Encoderscited by 0
  14. 2024ADAPT to Robustify Prompt Tuning Vision Transformerscited by 0
  15. 2024IAE: Irony-based Adversarial Examples for Sentiment Analysis Systemscited by 0
  16. 2024R.I.P.: A Simple Black-box Attack on Continual Test-time Adaptationcited by 0