mlsanityData to 7 Oct 2026

Generating Fluent Adversarial Examples for Natural Languages

arXiv 2007.06174 ↗First posted 13 Jul 2020cs.CLcited by 49

Not on the map. Why?

Abstract (arXiv)

Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge. Firstly, as the sentence space is discrete, it is difficult to make small perturbations along the direction of gradients. Secondly, the fluency of the generated examples cannot be guaranteed. In this paper, we propose MHA, which addresses both problems by performing Metropolis-Hastings sampling, whose proposal is designed with the guidance of gradients. Experiments on IMDB and SNLI show that our proposed MHA outperforms the baseline model on attacking capability. Adversarial training with MAH also leads to better robustness and performance.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 24; 2022: 14; 2023: 5; 2024: 5; 2025: 1.

49 papers.

Sort:

By area:

  1. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  2. 2021Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Modelscited by 219
  3. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  4. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  5. 2021Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitutioncited by 85
  6. 2021Towards Robustness Against Natural Language Word Substitutionscited by 68
  7. 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
  8. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  9. 2021Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysiscited by 30
  10. 2022Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitutioncited by 28
  11. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25
  12. 2021Reliability Testing for Natural Language Processing Systemscited by 25
37 more
  1. 2021Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglotscited by 23
  2. 2022Phrase-level Textual Adversarial Attack with Label Preservationcited by 23
  3. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  4. 2022TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimizationcited by 21
  5. 2024Assessing Adversarial Robustness of Large Language Models: An Empirical Studycited by 21
  6. 2021Certified Robustness to Programmable Transformations in LSTMscited by 18
  7. 2021Efficient Combinatorial Optimization for Word-level Adversarial Textual Attackcited by 17
  8. 2021Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluationcited by 16
  9. 2022A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictionscited by 15
  10. 2021Token-Modification Adversarial Attacks for Natural Language Processing: A Surveycited by 12
  11. 2022Robust Textual Embedding against Word-level Adversarial Attackscited by 12
  12. 2022DIMBA: Discretely Masked Black-Box Attack in Single Object Trackingcited by 11
  13. 2022TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attackcited by 10
  14. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  15. 2021BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classificationcited by 9
  16. 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 9
  17. 2021Improving the robustness and accuracy of biomedical language models through adversarial trainingcited by 7
  18. 2021Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Modelscited by 5
  19. 2022Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbscited by 5
  20. 2022Measuring Geographic Performance Disparities of Offensive Language Classifierscited by 5
  21. 2023Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimizationcited by 4
  22. 2022Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Taskcited by 3
  23. 2023Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacycited by 3
  24. 2023NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logiccited by 3
  25. 2021Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representationscited by 2
  26. 2024Enhancing adversarial robustness in Natural Language Inference using explanationscited by 2
  27. 2021Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Modelscited by 1
  28. 2022MUC-driven Feature Importance Measurement and Adversarial Analysis for Random Forestcited by 1
  29. 2023Hiding Backdoors within Event Sequence Data via Poisoning Attackscited by 1
  30. 2024Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generationcited by 1
  31. 2021Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classificationcited by 0
  32. 2021DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstructioncited by 0
  33. 2021SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Textcited by 0
  34. 2022Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanationscited by 0
  35. 2024Reversible Jump Attack to Textual Classifiers with Modification Reductioncited by 0
  36. 2024IAE: Irony-based Adversarial Examples for Sentiment Analysis Systemscited by 0
  37. 2025Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attackscited by 0