mlsanityData to 7 Oct 2026

It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness

arXiv 2303.09767 ↗First posted 17 Mar 2023cs.LG cs.CRcited by 9

Not on the map. Why?

Abstract (arXiv)

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to confuse the model into making a mistake. Such examples pose a serious threat to the applicability of machine-learning-based systems, especially in life- and safety-critical domains. To address this problem, the area of adversarial robustness investigates mechanisms behind adversarial attacks and defenses against these attacks. This survey reviews a particular subset of this literature that focuses on investigating properties of training data in the context of model robustness under evasion attacks. It first summarizes the main properties of data leading to adversarial vulnerability. It then discusses guidelines and techniques for improving adversarial robustness by enhancing the data representation and learning procedures, as well as techniques for estimating robustness guarantees given particular data. Finally, it discusses gaps of knowledge and promising future research directions in this area.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 131 of its 217 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

131 of 217 references.

References · 131

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  12. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
38 more
  1. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  2. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  3. 2016Adversarial Machine Learning at Scalecited by 934
  4. 2018Robustness May Be at Odds with Accuracycited by 873
  5. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  6. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  7. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  8. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  9. 2017Interpretation of Neural Networks is Fragilecited by 443
  10. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  11. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  12. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  13. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  14. 2018Adversarially Robust Generalization Requires More Datacited by 318
  15. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
  16. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  17. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
  18. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  19. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  20. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  21. 2019Intrinsic dimension of data representations in deep neural networkscited by 276
  22. 2018Adversarial Attacks and Defences: A Surveycited by 259
  23. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  24. 2021Improving Robustness using Generated Datacited by 233
  25. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  26. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  27. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 208
  28. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  29. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 171
  30. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  31. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  32. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  33. 2018Rademacher Complexity for Adversarially Robust Generalizationcited by 132
  34. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  35. 2018Are adversarial examples inevitable?cited by 113
  36. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  37. 2021On Interaction Between Augmentations and Corruptions in Natural Corruption Robustnesscited by 98
  38. 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97

50 most cited of 131 All 131 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 1.

9 papers.

  1. 2025Impact of Data Duplication on Deep Neural Network-Based Image Classifiers: Robust vs. Standard Modelscited by 4
  2. 2025Alleviating Performance Disparity in Adversarial Spatiotemporal Graph Learning Under Zero-Inflated Distributioncited by 2
  3. 2024A practical generalization metric for deep networks benchmarkingcited by 1
  4. 2025Beyond the Generative Learning Trilemma: Generative Model Assessment in Data Scarcity Domainscited by 1
  5. 2025Adversarial Robustness of Nonparametric Regressioncited by 1
  6. 2024On Adversarial Robustness of Language Models in Transfer Learningcited by 0
  7. 2025Soft Weighted Machine Unlearningcited by 0
  8. 2025BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuningcited by 0
  9. 2026Building Trust in Artificial Intelligence: A Necessity for Railway Applicationscited by 0