mlsanityData to 14 Oct 2026

Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks

arXiv 2106.09223 ↗First posted 17 Jun 2021cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

To evaluate the robustness gain of Bayesian neural networks on image classification tasks, we perform input perturbations, and adversarial attacks to the state-of-the-art Bayesian neural networks, with a benchmark CNN model as reference. The attacks are selected to simulate signal interference and cyberattacks towards CNN-based machine learning systems. The result shows that a Bayesian neural network achieves significantly higher robustness against adversarial attacks generated against a deterministic neural network model, without adversarial training. The Bayesian posterior can act as the safety precursor of ongoing malicious activities. Furthermore, we show that the stochastic classifier after the deterministic CNN extractor has sufficient robustness enhancement rather than a stochastic feature extractor before the stochastic classifier. This advises on utilizing stochastic layers in building decision-making pipelines within a safety-critical domain.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 17 of its 25 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

17 of 25 references.

References · 17

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  6. 2017Random Erasing Data Augmentationcited by 1,239
  7. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  8. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  9. 2015Variational Dropout and the Local Reparameterization Trickcited by 490
  10. 2019On Evaluating Adversarial Robustnesscited by 447
  11. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  12. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
5 more
  1. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  2. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  3. 2019The Limitations of Adversarial Training and the Blind-Spot Attackcited by 63
  4. 2019Statistical Guarantees for the Robustness of Bayesian Neural Networkscited by 35
  5. 2017Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examplescited by 27

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 2; 2025: 0; 2026: 1.

6 papers.

  1. 2023Adversarial Bayesian Augmentation for Single-Source Domain Generalizationcited by 22
  2. 2022On the Robustness of Bayesian Neural Networks to Adversarial Attackscited by 12
  3. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 9
  4. 2024Tight Verification of Probabilistic Robustness in Bayesian Neural Networkscited by 5
  5. 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networkscited by 2
  6. 2026Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layerscited by 0