mlsanityData to 7 Oct 2026

Generating Natural Adversarial Examples

arXiv 1710.11342 ↗First posted 31 Oct 2017cs.LG cs.AI cs.CLcited by 182

Not on the map. Why?

Abstract (arXiv)

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in substantially different model predictions, is helpful in evaluating the robustness of these models by exposing the adversarial scenarios where they fail. However, these malicious perturbations are often unnatural, not semantically meaningful, and not applicable to complicated domains such as language. In this paper, we propose a framework to generate natural and legible adversarial examples that lie on the data manifold, by searching in semantic space of dense and continuous data representation, utilizing the recent advances in generative adversarial networks. We present generated adversaries to demonstrate the potential of the proposed approach for black-box classifiers for a wide range of applications such as image classification, textual entailment, and machine translation. We include experiments to show that the generated adversaries are natural, legible to humans, and useful in evaluating and analyzing black-box classifiers.

Key facts. Cited by 182 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 56; 2022: 38; 2023: 44; 2024: 24; 2025: 12; 2026: 8.

182 papers.

Sort:

By area:

  1. 2022Red Teaming Language Models with Language Modelscited by 983
  2. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Modelscited by 307
  3. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  4. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  5. 2023Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMscited by 117
  6. 2021Adversarial Examples Make Strong Poisonscited by 115
  7. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  8. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  9. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  10. 2022The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Trainingcited by 85
  11. 2021Improving Transferability of Adversarial Patches on Face Recognition with Generative Modelscited by 80
  12. 2022Diffusion Models for Counterfactual Explanationscited by 79
38 more
  1. 2021Bad Characters: Imperceptible NLP Attackscited by 69
  2. 2021Towards Robustness Against Natural Language Word Substitutionscited by 68
  3. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  4. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  5. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  6. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  7. 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
  8. 2023Adversarial Counterfactual Visual Explanationscited by 47
  9. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  10. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
  11. 2023On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codexcited by 41
  12. 2021TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systemscited by 36
  13. 2024Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Modelscited by 36
  14. 2021A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attackscited by 33
  15. 2021Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processingcited by 30
  16. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  17. 2021Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Modelscited by 29
  18. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  19. 2023Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibilitycited by 28
  20. 2024Universal Prompt Optimizer for Safe Text-to-Image Generationcited by 27
  21. 2022Certified Robustness Against Natural Language Attacks by Causal Interventioncited by 23
  22. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  23. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  24. 2021Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answeringcited by 20
  25. 2023A Survey on Out-of-Distribution Evaluation of Neural NLP Modelscited by 20
  26. 2022RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answeringcited by 19
  27. 2022Textual Manifold-based Defense Against Natural Language Adversarial Examplescited by 19
  28. 2023Robustifying Token Attention for Vision Transformerscited by 19
  29. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  30. 2022Attacking deep networks with surrogate-based adversarial black-box methods is easycited by 18
  31. 2021Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Modelscited by 17
  32. 2021Attack to Fool and Explain Deep Networkscited by 17
  33. 2021Efficient Combinatorial Optimization for Word-level Adversarial Textual Attackcited by 17
  34. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  35. 2022Shilling Black-box Recommender Systems by Learning to Generate Fake User Profilescited by 15
  36. 2022TASA: Deceiving Question Answering Models by Twin Answer Sentences Attackcited by 15
  37. 2024Global Counterfactual Directionscited by 15
  38. 2024Rethinking Visual Counterfactual Explanations Through Region Constraintcited by 14

50 most cited of 182 All 182 (JSON)