mlsanityData to 7 Oct 2026

Towards Crafting Text Adversarial Samples

arXiv 1707.02812 ↗First posted 10 Jul 2017cs.LG cs.AI cs.CLcited by 55

Not on the map. Why?

Abstract (arXiv)

Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being mis-classified by the classifier. However, the samples are perceived to be drawn from entirely different classes and thus it becomes hard to detect the adversarial samples. Most of the prior works have been focused on synthesizing adversarial samples in the image domain. In this paper, we propose a new method of crafting adversarial text samples by modification of the original samples. Modifications of the original text samples are done by deleting or replacing the important or salient words in the text or by introducing new words in the text sample. Our algorithm works best for the datasets which have sub-categories within each of the classes of examples. While crafting adversarial samples, one of the key constraint is to generate meaningful sentences which can at pass off as legitimate from language (English) viewpoint. Experimental results on IMDB movie review dataset for sentiment analysis and Twitter dataset for gender detection show the efficiency of our proposed method.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 12; 2023: 10; 2024: 10; 2025: 3; 2026: 1.

55 papers.

Sort:

By area:

  1. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  2. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  3. 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
  4. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  5. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  6. 2021Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processingcited by 30
  7. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  8. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  9. 2023Evaluating the Robustness of Discrete Promptscited by 18
  10. 2021Security and Privacy for Artificial Intelligence: Opportunities and Challengescited by 16
  11. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  12. 2024Multi-granular Adversarial Attacks against Black-box Neural Ranking Modelscited by 14
38 more
  1. 2021Token-Modification Adversarial Attacks for Natural Language Processing: A Surveycited by 12
  2. 2021Fall of Giants: How popular text-based MLaaS fall against a simple evasion attackcited by 12
  3. 2022Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretationcited by 12
  4. 2024Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxiacited by 12
  5. 2024Spiking Convolutional Neural Networks for Text Classificationcited by 10
  6. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  7. 2024A Modified Word Saliency-Based Adversarial Attack on Text Classification Modelscited by 9
  8. 2021Evaluating Document Coherence Modellingcited by 8
  9. 2022Residue-Based Natural Language Adversarial Attack Detectioncited by 8
  10. 2022Efficient Adversarial Training With Data Pruningcited by 7
  11. 2022Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Featurescited by 7
  12. 2023CT-GAT: Cross-Task Generative Adversarial Attack based on Transferabilitycited by 6
  13. 2022Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbscited by 5
  14. 2024ProTransformer: Robustify Transformers via Plug-and-Play Paradigmcited by 5
  15. 2022Dynamic Time Warping based Adversarial Framework for Time-Series Domaincited by 4
  16. 2022EDoG: Adversarial Edge Detection For Graph Neural Networkscited by 4
  17. 2022Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputscited by 3
  18. 2023Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacycited by 3
  19. 2024Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descentcited by 3
  20. 2021TREATED:Towards Universal Defense against Textual Adversarial Attackscited by 2
  21. 2021Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representationscited by 2
  22. 2023Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translationcited by 2
  23. 2024Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networkscited by 2
  24. 2021Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Modelscited by 1
  25. 2021Quantifying and Understanding Adversarial Examples in Discrete Input Spacescited by 1
  26. 2022Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysiscited by 1
  27. 2023Analyzing the Impact of Adversarial Examples on Explainable Machine Learningcited by 1
  28. 2024Counteracting Concept Drift by Learning with Future Malware Predictionscited by 1
  29. 2025A Comprehensive Analysis of Adversarial Attacks against Spam Filterscited by 1
  30. 2021Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classificationcited by 0
  31. 2021Robustness Tests of NLP Machine Learning Models: Search and Semantically Replacecited by 0
  32. 2021Evaluating Deception Detection Model Robustness To Linguistic Variationcited by 0
  33. 2021Learning Neural Models for Natural Language Processing in the Face of Distributional Shiftcited by 0
  34. 2021AED: An black-box NLP classifier model attackercited by 0
  35. 2021Repairing Adversarial Texts through Perturbationcited by 0
  36. 2022Probabilistic Categorical Adversarial Attack & Adversarial Trainingcited by 0
  37. 2023Evaluating the Robustness of Conversational Recommender Systems by Adversarial Examplescited by 0
  38. 2023Machine Translation Models Stand Strong in the Face of Adversarial Attackscited by 0

50 most cited of 55 All 55 (JSON)