mlsanityData to 13 Oct 2026

The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networks

arXiv 2101.02689 ↗First posted 7 Jan 2021stat.ML cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

It is desirable, and often a necessity, for machine learning models to be robust against adversarial attacks. This is particularly true for Bayesian models, as they are well-suited for safety-critical applications, in which adversarial attacks can have catastrophic outcomes. In this work, we take a deeper look at the adversarial robustness of Bayesian Neural Networks (BNNs). In particular, we consider whether the adversarial robustness of a BNN can be increased by model choices, particularly the Lipschitz continuity induced by the prior. Conducting in-depth analysis on the case of i.i.d., zero-mean Gaussian priors and posteriors approximated via mean-field variational inference, we find evidence that adversarial robustness is indeed sensitive to the prior variance.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 7 Jan 2021.

Builds on

29 of 39 references.

References · 29

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,336
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,379
  3. 2013Intriguing properties of neural networkscited by 5,137
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,862
  6. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 742
  7. 2020Fast is better than free: Revisiting adversarial trainingcited by 725
  8. 2015Weight Uncertainty in Neural Networkscited by 554
  9. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  10. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  11. 2018Feature Denoising for Improving Adversarial Robustnesscited by 313
  12. 2016Safety Verification of Deep Neural Networkscited by 263
17 more
  1. 2017Detecting Adversarial Samples from Artifactscited by 244
  2. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  3. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  4. 2019Functional Variational Bayesian Neural Networkscited by 127
  5. 2019When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attackscited by 87
  6. 2018Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Networkcited by 69
  7. 2019ME-Net: Towards Effective Adversarial Robustness with Matrix Estimationcited by 65
  8. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 62
  9. 2020Robustness of Bayesian Neural Networks to Gradient-Based Attackscited by 48
  10. 2020Probabilistic Safety for Bayesian Neural Networkscited by 42
  11. 2019Provable robustness against all adversarial lp-perturbations for p≥ 1cited by 39
  12. 2019Statistical Guarantees for the Robustness of Bayesian Neural Networkscited by 35
  13. 2017Intriguing Properties of Adversarial Examplescited by 20
  14. 2019Bayesian Learning-Based Adaptive Control for Safety Critical Systemscited by 19
  15. 2018The Limitations of Model Uncertainty in Adversarial Settingscited by 14
  16. 2019Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"cited by 12
  17. 2019Adversarial Robustness Guarantees for Classification with Gaussian Processescited by 11

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 1.

3 papers.

  1. 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
  2. 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networkscited by 2
  3. 2026Lipschitz bounds for integral kernelscited by 0