mlsanityData to 14 Oct 2026

BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming

arXiv 2306.10742 ↗First posted 19 Jun 2023cs.LG stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce BNN-DP, an efficient algorithmic framework for analysis of adversarial robustness of Bayesian Neural Networks (BNNs). Given a compact set of input points Tsubset ℝn, BNN-DP computes lower and upper bounds on the BNN's predictions for all the points in T. The framework is based on an interpretation of BNNs as stochastic dynamical systems, which enables the use of Dynamic Programming (DP) algorithms to bound the prediction range along the layers of the network. Specifically, the method uses bound propagation techniques and convex relaxations to derive a backward recursion procedure to over-approximate the prediction range of the BNN with piecewise affine functions. The algorithm is general and can handle both regression and classification tasks. On a set of experiments on various regression and classification tasks and BNN architectures, we show that BNN-DP outperforms state-of-the-art methods by up to four orders of magnitude in both tightness of the bounds and computational efficiency.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 19 Jun 2023.

Builds on

28 of 38 references.

References · 28

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  5. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  6. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  7. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  8. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  9. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  10. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
  11. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  12. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
16 more
  1. 2019Practical Deep Learning with Bayesian Principlescited by 158
  2. 2018Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adamcited by 131
  3. 2017Noisy Natural Gradient as Variational Inferencecited by 94
  4. 2017Uncertainty-Aware Reinforcement Learning for Collision Avoidancecited by 88
  5. 2020Robustness of Bayesian Neural Networks to Gradient-Based Attackscited by 48
  6. 2020Probabilistic Safety for Bayesian Neural Networkscited by 42
  7. 2019Statistical Guarantees for the Robustness of Bayesian Neural Networkscited by 35
  8. 2020Lagrangian Decomposition for Neural Network Verificationcited by 35
  9. 2021Bayesian Inference with Certifiable Adversarial Robustnesscited by 26
  10. 2018Robustness Guarantees for Bayesian Inference with Gaussian Processescited by 23
  11. 2022Individual Fairness Guarantees for Neural Networkscited by 23
  12. 2021Make Sure You're Unsure: A Framework for Verifying Probabilistic Specificationscited by 18
  13. 2021Infinite Time Horizon Safety of Bayesian Neural Networkscited by 13
  14. 2017Adversarial Phenomenon in the Eyes of Bayesian Deep Learningcited by 11
  15. 2019Adversarial Vulnerability Bounds for Gaussian Process Classificationcited by 5
  16. 2021Adversarial Robustness Guarantees for Gaussian Processescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 0; 2026: 2.

8 papers.

  1. 2024Certified Robustness to Data Poisoning in Gradient-Based Trainingcited by 18
  2. 2023Adversarial Robustness Certification for Bayesian Neural Networkscited by 7
  3. 2024Tight Verification of Probabilistic Robustness in Bayesian Neural Networkscited by 5
  4. 2024Solving Probabilistic Verification Problems of Neural Networks using Branch and Boundcited by 4
  5. 2024Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selectioncited by 3
  6. 2024Risk-Averse Certification of Bayesian Neural Networkscited by 0
  7. 2026Clustered Randomized Smoothing for Stochastic Prediction Functionscited by 0
  8. 2026Certified Uncertainty Propagation in One-Shot Federated Bayesian Models via Posterior Event Transportcited by 0