mlsanityData to 7 Oct 2026

Are Generative Classifiers More Robust to Adversarial Attacks?

arXiv 1802.06552 ↗First posted 19 Feb 2018cs.LG stat.MLcited by 36

Not on the map. Why?

Abstract (arXiv)

There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative classifiers, which only model the conditional distribution of the labels given the inputs. In this paper, we propose and investigate the deep Bayes classifier, which improves classical naive Bayes with conditional deep generative models. We further develop detection methods for adversarial examples, which reject inputs with low likelihood under the generative model. Experimental results suggest that deep Bayes classifiers are more robust than deep discriminative classifiers, and that the proposed detection methods are effective against many recently proposed attacks.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 10; 2023: 4; 2024: 2; 2025: 5; 2026: 2.

36 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  3. 2023Robust Classification via a Single Diffusion Modelcited by 79
  4. 2021Towards Robustness Against Natural Language Word Substitutionscited by 68
  5. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  6. 2021Meta Gradient Adversarial Attackcited by 55
  7. 2021Score-Based Generative Classifierscited by 53
  8. 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
  9. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
  10. 2021Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Themcited by 46
  11. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  12. 2022On the Limitations of Stochastic Pre-processing Defensescited by 21
24 more
  1. 2022Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlocited by 19
  2. 2021Adversarial Visual Robustness by Causal Interventioncited by 13
  3. 2022GenLabel: Mixup Relabeling using Generative Modelscited by 10
  4. 2023Multiscale Flow for Robust and Optimal Cosmological Analysiscited by 10
  5. 2025Generative or Discriminative? Revisiting Text Classification in the Era of Transformerscited by 9
  6. 2022Machine Learning in NextG Networks via Generative Adversarial Networkscited by 8
  7. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  8. 2021The art of defense: letting networks fool the attackercited by 6
  9. 2021Adaptive Perturbation for Adversarial Attackcited by 6
  10. 2022Generative multitask learning mitigates target-causing confoundingcited by 4
  11. 2022Wavelet Regularization Benefits Adversarial Trainingcited by 3
  12. 2023Improving Transferability of Adversarial Examples via Bayesian Attackscited by 3
  13. 2025Your VAR Model is Secretly an Efficient and Explainable Generative Classifiercited by 2
  14. 2021Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attackscited by 1
  15. 2022Beyond NaN: Resiliency of Optimization Layers in The Face of Infeasibilitycited by 1
  16. 2021Target Training Does Adversarial Training Without Adversarial Samplescited by 0
  17. 2021Boltzmann Tuning of Generative Modelscited by 0
  18. 2024Transferable 3D Adversarial Shape Completion using Diffusion Modelscited by 0
  19. 2024Causal Interpretability for Adversarial Robustness: A Hybrid Generative Classification Approachcited by 0
  20. 2025Generative Classifier for Domain Generalizationcited by 0
  21. 2025Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustnesscited by 0
  22. 2025Sparse Representations Improve Adversarial Robustness of Neural Network Classifierscited by 0
  23. 2026Generative Cross-Entropy: A Strictly Proper Loss for Data-Efficient Classificationcited by 0
  24. 2026Generative Bayesian Filtering for State Estimationcited by 0