mlsanityData to 7 Oct 2026

Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers

arXiv 2203.05948 ↗First posted 11 Mar 2022cs.CL cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples. In this paper, we propose a gradient-based adversarial attack against transformer-based text classifiers. The adversarial perturbation in our method is imposed to be block-sparse so that the resultant adversarial example differs from the original sentence in only a few words. Due to the discrete nature of textual data, we perform gradient projection to find the minimizer of our proposed optimization problem. Experimental results demonstrate that, while our adversarial attack maintains the semantics of the sentence, it can reduce the accuracy of GPT-2 to less than 5% on different datasets (AG News, MNLI, and Yelp Reviews). Furthermore, the block-sparsity constraint of the proposed optimization problem results in small perturbations in the adversarial example.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 11 Mar 2022.

Builds on

17 of 21 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  9. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
  10. 2018Universal Sentence Encodercited by 485
  11. 2018Generating Natural Language Adversarial Examplescited by 422
  12. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
5 more
  1. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  2. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  3. 2016Crafting Adversarial Input Sequences for Recurrent Neural Networkscited by 102
  4. 2018Interpretable Adversarial Perturbation in Input Embedding Space for Textcited by 67
  5. 2019Word-level Textual Adversarial Attacking as Combinatorial Optimizationcited by 37

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 2; 2025: 3.

9 papers.

  1. 2023TransFool: An Adversarial Attack against Neural Machine Translation Modelscited by 12
  2. 2023Targeted Adversarial Attacks against Neural Machine Translationcited by 10
  3. 2023A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translationcited by 4
  4. 2023Translate your gibberish: black-box adversarial attack on machine translation systemscited by 2
  5. 2024BinarySelect to Improve Accessibility of Black-Box Attack Researchcited by 1
  6. 2024NMT-Obfuscator Attack: Ignore a sentence in translation with only one wordcited by 0
  7. 2025Extend Adversarial Policy Against Neural Machine Translation via Unknown Tokencited by 0
  8. 2025RedHerring Attack: Testing the Reliability of Attack Detectioncited by 0
  9. 2025Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithmscited by 0