mlsanityData to 7 Oct 2026

Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey

arXiv 2303.06302 ↗First posted 11 Mar 2023cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks and defenses in machine learning and deep neural network have been gaining significant attention due to the rapidly growing applications of deep learning in the Internet and relevant scenarios. This survey provides a comprehensive overview of the recent advancements in the field of adversarial attack and defense techniques, with a focus on deep neural network-based classification models. Specifically, we conduct a comprehensive classification of recent adversarial attack methods and state-of-the-art adversarial defense techniques based on attack principles, and present them in visually appealing tables and tree diagrams. This is based on a rigorous evaluation of the existing works, including an analysis of their strengths and limitations. We also categorize the methods into counter-attack detection and robustness enhancement, with a specific focus on regularization-based methods for enhancing robustness. New avenues of attack are also explored, including search-based, decision-based, drop-based, and physical-world attacks, and a hierarchical classification of the latest defense methods is provided, highlighting the challenges of balancing training costs with performance, maintaining clean accuracy, overcoming the effect of gradient masking, and ensuring method transferability. At last, the lessons learned and open challenges are summarized with future research opportunities recommended.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 120 of its 261 references that are in the map. First posted on arXiv 11 Mar 2023.

Builds on

120 of 261 references.

References · 120

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2019Searching for MobileNetV3cited by 1,984
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  11. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  12. 2016Adversarial Machine Learning at Scalecited by 934
38 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  2. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  3. 2016Universal adversarial perturbationscited by 774
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  5. 2017One pixel attack for fooling deep neural networkscited by 579
  6. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  7. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  8. 2018Adversarial Attack on Graph Structured Datacited by 300
  9. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  10. 2020The Creation and Detection of Deepfakes: A Surveycited by 246
  11. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  12. 2019Hypergraph Convolution and Hypergraph Attentioncited by 226
  13. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  14. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  15. 2019Self-Driving Cars: A Surveycited by 147
  16. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  17. 2020Understanding Gradient Clipping in Private SGD: A Geometric Perspectivecited by 140
  18. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  19. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  20. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 123
  21. 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 98
  22. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  23. 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
  24. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  25. 2016Measuring Neural Net Robustness with Constraintscited by 90
  26. 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
  27. 2020Evading Deepfake-Image Detectors with White- and Black-Box Attackscited by 80
  28. 2020Towards Transferable Adversarial Attack against Deep Face Recognitioncited by 79
  29. 2020Imitation Attacks and Defenses for Black-box Machine Translation Systemscited by 78
  30. 2019Metric Learning for Adversarial Robustnesscited by 77
  31. 2021Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Bettercited by 77
  32. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 76
  33. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  34. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
  35. 2019Training Robust Deep Neural Networks via Adversarial Noise Propagationcited by 60
  36. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  37. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  38. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55

50 most cited of 120 All 120 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 4.

5 papers.

  1. 2024Can Your Generative Model Detect Out-of-Distribution Covariate Shift?cited by 4
  2. 2025Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizerscited by 4
  3. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  4. 2025ExplainableGuard: Interpretable Adversarial Defense for Large Language Models Using Chain-of-Thought Reasoningcited by 0
  5. 2025Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attackscited by 0