mlsanityData to 7 Oct 2026

The robust way to stack and bag: the local Lipschitz way

arXiv 2206.00513 ↗First posted 1 Jun 2022cs.LG cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

Recent research has established that the local Lipschitz constant of a neural network directly influences its adversarial robustness. We exploit this relationship to construct an ensemble of neural networks which not only improves the accuracy, but also provides increased adversarial robustness. The local Lipschitz constants for two different ensemble methods - bagging and stacking - are derived and the architectures best suited for ensuring adversarial robustness are deduced. The proposed ensemble architectures are tested on MNIST and CIFAR-10 datasets in the presence of white-box attacks, FGSM and PGD. The proposed architecture is found to be more robust than a) a single network and b) traditional ensemble methods.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 1 Jun 2022.

Builds on

18 of 26 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016Adversarial Machine Learning at Scalecited by 934
  4. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  5. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  6. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
  7. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 290
  8. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  9. 2021Ensemble deep learning: A reviewcited by 283
  10. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  11. 2018Sorting out Lipschitz function approximationcited by 211
  12. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
6 more
  1. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
  2. 2020Exactly Computing the Local Lipschitz Constant of ReLU Networkscited by 102
  3. 2020Do Wider Neural Networks Really Help Adversarial Robustness?cited by 79
  4. 2019Adversarially Robust Generalization Just Requires More Unlabeled Datacited by 75
  5. 2020Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networkscited by 7
  6. 2017An aggregating strategy for shifting experts in discrete sequence predictioncited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysiscited by 16
  2. 2025TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justificationcited by 2
  3. 2024Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classificationcited by 0