mlsanityData to 14 Oct 2026

Adversarial Examples in Modern Machine Learning: A Review

arXiv 1911.05268 ↗First posted 13 Nov 2019cs.LG cs.AI cs.CRcited by 36

Not on the map. Why?

Abstract (arXiv)

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on machine learning models in the visual domain, where methods for generating and detecting such examples have been most extensively studied. We explore a variety of adversarial attack methods that apply to image-space content, real world adversarial attacks, adversarial defenses, and the transferability property of adversarial examples. We also discuss strengths and weaknesses of various methods of adversarial attack and defense. Our aim is to provide an extensive coverage of the field, furnishing the reader with an intuitive understanding of the mechanics of adversarial attack and defense mechanisms and enlarging the community of researchers studying this fundamental set of problems.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 9; 2023: 10; 2024: 5; 2025: 0; 2026: 3.

36 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  2. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  3. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 44
  4. 2022Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overviewcited by 37
  5. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 25
  6. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Basescited by 18
  7. 2021Physically Consistent Neural Networks for building thermal modeling: theory and analysiscited by 17
  8. 2021Security and Privacy for Artificial Intelligence: Opportunities and Challengescited by 16
  9. 2023Physical Adversarial Attacks for Surveillance: A Surveycited by 15
  10. 2022On the Robustness of Bayesian Neural Networks to Adversarial Attackscited by 12
  11. 2023SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detectioncited by 10
  12. 2023Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Surveycited by 5
24 more
  1. 2021EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attackscited by 4
  2. 2024A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunitiescited by 4
  3. 2021Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoisingcited by 3
  4. 2023Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systemscited by 3
  5. 2023AdvFAS: A robust face anti-spoofing framework against adversarial examplescited by 3
  6. 2024Arabic Synonym BERT-based Adversarial Examples for Text Classificationcited by 3
  7. 2024RenderBender: A Survey on Adversarial Attacks Using Differentiable Renderingcited by 3
  8. 2021Comparison of semi-supervised deep learning algorithms for audio classificationcited by 2
  9. 2023Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Trainingcited by 2
  10. 2021Localized Uncertainty Attackscited by 1
  11. 2021Improving Adversarial Robustness for Free with Snapshot Ensemblecited by 1
  12. 2022An Exploration of How Training Set Composition Bias in Machine Learning Affects Identifying Rare Objectscited by 1
  13. 2022An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Modelscited by 1
  14. 2023The Pros and Cons of Adversarial Robustnesscited by 1
  15. 2024ADAPT: A Game-Theoretic and Neuro-Symbolic Framework for Automated Distributed Adaptive Penetration Testingcited by 1
  16. 2021BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attackscited by 0
  17. 2022Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classificationcited by 0
  18. 2022Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbationscited by 0
  19. 2022A study on the deviations in performance of FNNs and CNNs in the realm of grayscale adversarial imagescited by 0
  20. 2023Human-Imperceptible Identification with Learnable Lensless Imagingcited by 0
  21. 2023From text to multimodal: a survey of adversarial example generation in question answering systemscited by 0
  22. 2026Generating adversarial inputs for a graph neural network model of AC power flowcited by 0
  23. 2026Evaluation of Adversarial Robustness in Arabic Language Modelscited by 0
  24. 2026Correcting Learning-based Perception for Safetycited by 0