mlsanityData to 7 Oct 2026

Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network

arXiv 1810.01279 ↗First posted 1 Oct 2018cs.LG cs.AI cs.CRcited by 68

Not on the map. Why?

Abstract (arXiv)

We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness of neural networks (Liu 2017), we noticed that adding noise blindly to all the layers is not the optimal way to incorporate randomness. Instead, we model randomness under the framework of Bayesian Neural Network (BNN) to formally learn the posterior distribution of models in a scalable way. Second, we formulate the mini-max problem in BNN to learn the best model distribution under adversarial attacks, leading to an adversarial-trained Bayesian neural net. Experiment results demonstrate that the proposed algorithm achieves state-of-the-art performance under strong attacks. On CIFAR-10 with VGG network, our model leads to 14% accuracy improvement compared with adversarial training (Madry 2017) and random self-ensemble (Liu 2017) under PGD attack with 0.035 distortion, and the gap becomes even larger on a subset of ImageNet.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 14; 2023: 16; 2024: 7; 2025: 8; 2026: 2.

68 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  3. 2021GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularizationcited by 34
  4. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  5. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  6. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  7. 2021Bayesian Inference with Certifiable Adversarial Robustnesscited by 26
  8. 2023Adversarial Bayesian Augmentation for Single-Source Domain Generalizationcited by 21
  9. 2021SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluationcited by 16
  10. 2022Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervisioncited by 16
  11. 2021Being a Bit Frequentist Improves Bayesian Neural Networkscited by 15
  12. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
38 more
  1. 2022Demystifying the Adversarial Robustness of Random Transformation Defensescited by 14
  2. 2022On the Robustness of Bayesian Neural Networks to Adversarial Attackscited by 12
  3. 2023Robust low-rank training via approximate orthonormal constraintscited by 12
  4. 2021Adversarial Feature Augmentation and Normalization for Visual Recognitioncited by 11
  5. 2025Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspectivecited by 10
  6. 2021Fast Gradient Non-sign Methodscited by 9
  7. 2021Certification of Iterative Predictions in Bayesian Neural Networkscited by 8
  8. 2021Adversarial Attack and Defense in Deep Rankingcited by 8
  9. 2021Bayesian Inference Forgettingcited by 7
  10. 2023Adversarial Robustness Certification for Bayesian Neural Networkscited by 7
  11. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 7
  12. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  13. 2021The art of defense: letting networks fool the attackercited by 6
  14. 2021Inverting Adversarially Robust Networks for Image Synthesiscited by 6
  15. 2022Data-Efficient Double-Win Lottery Tickets from Robust Pre-trainingcited by 5
  16. 2023Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Modelscited by 5
  17. 2025Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attackscited by 5
  18. 2021Robustness of Bayesian Neural Networks to White-Box Adversarial Attackscited by 4
  19. 2022Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defensecited by 4
  20. 2023Probabilistic Reach-Avoid for Bayesian Neural Networkscited by 4
  21. 2024Inferring the Langevin Equation with Uncertainty via Bayesian Neural Networkscited by 4
  22. 2021The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networkscited by 3
  23. 2022Wavelet Regularization Benefits Adversarial Trainingcited by 3
  24. 2023Individual Fairness in Bayesian Neural Networkscited by 3
  25. 2023Improving Transferability of Adversarial Examples via Bayesian Attackscited by 3
  26. 2026Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformerscited by 3
  27. 2021Adversarial Examples Detection with Bayesian Neural Networkcited by 2
  28. 2022Rethinking Feature Uncertainty in Stochastic Neural Networks for Adversarial Robustnesscited by 2
  29. 2022An Eye for an Eye: Defending against Gradient-based Attacks with Gradientscited by 2
  30. 2022Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognitioncited by 2
  31. 2022Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defensecited by 2
  32. 2022Attacking Adversarial Defences by Smoothing the Loss Landscapecited by 2
  33. 2023Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizercited by 2
  34. 2023Towards Certified Probabilistic Robustness with High Accuracycited by 2
  35. 2023A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networkscited by 2
  36. 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networkscited by 2
  37. 2024Spectral regularization for adversarially-robust representation learningcited by 2
  38. 2021Defensive Tensorizationcited by 1

50 most cited of 68 All 68 (JSON)