mlsanityData to 14 Oct 2026

TREATED:Towards Universal Defense against Textual Adversarial Attacks

arXiv 2109.06176 ↗First posted 13 Sep 2021cs.LG cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection methods usually make assumptions about the adversarial example and attack method (e.g., the word frequency of the adversarial example, the perturbation level of the attack method). However, this limits the applicability of the detection method. To this end, we propose TREATED, a universal adversarial detection method that can defend against attacks of various perturbation levels without making any assumptions. TREATED identifies adversarial examples through a set of well-designed reference models. Extensive experiments on three competitive neural networks and two widely used datasets show that our method achieves better detection performance than baselines. We finally conduct ablation studies to verify the effectiveness of our method.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 48 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

36 of 48 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  7. 2016Adversarial Machine Learning at Scalecited by 936
  8. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  9. 2019Adversarial Training for Free!cited by 643
  10. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
  11. 2018Generating Natural Language Adversarial Examplescited by 424
  12. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
24 more
  1. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 381
  2. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 345
  3. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 286
  4. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  5. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  6. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 264
  7. 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 254
  8. 2017Detecting Adversarial Samples from Artifactscited by 245
  9. 2017On Detecting Adversarial Perturbationscited by 232
  10. 2017Generating Natural Adversarial Examplescited by 183
  11. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
  12. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  13. 2016Crafting Adversarial Input Sequences for Recurrent Neural Networkscited by 103
  14. 2020Spelling Error Correction with Soft-Masked BERTcited by 90
  15. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  16. 2021Towards Robustness Against Natural Language Word Substitutionscited by 69
  17. 2018Interpretable Adversarial Perturbation in Input Embedding Space for Textcited by 67
  18. 2019Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classificationcited by 57
  19. 2017Towards Crafting Text Adversarial Samplescited by 55
  20. 2020Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examplescited by 54
  21. 2020CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generationcited by 44
  22. 2020A Comprehensive Survey of Grammar Error Correctioncited by 17
  23. 2019Generating Black-Box Adversarial Examples for Text Classifiers Using a Deep Reinforced Modelcited by 10
  24. 2017Grammatical Error Correction with Neural Reinforcement Learningcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1.

3 papers.

  1. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 23
  2. 2023Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directionscited by 4
  3. 2022Don't sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attackscited by 3