mlsanityData to 7 Oct 2026

Building Robust Ensembles via Margin Boosting

arXiv 2206.03362 ↗First posted 7 Jun 2022cs.LG cs.AI cs.CRcited by 8

Not on the map. Why?

Abstract (arXiv)

In the context of adversarial robustness, a single model does not usually have enough power to defend against all possible adversarial attacks, and as a result, has sub-optimal robustness. Consequently, an emerging line of work has focused on learning an ensemble of neural networks to defend against adversarial attacks. In this work, we take a principled approach towards building robust ensembles. We view this problem from the perspective of margin-boosting and develop an algorithm for learning an ensemble with maximum margin. Through extensive empirical evaluation on benchmark datasets, we show that our algorithm not only outperforms existing ensembling techniques, but also large models trained in an end-to-end fashion. An important byproduct of our work is a margin-maximizing cross-entropy (MCE) loss, which is a better alternative to the standard cross-entropy (CE) loss. Empirically, we show that replacing the CE loss in state-of-the-art adversarial training techniques with our MCE loss leads to significant performance improvement.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 41 of its 75 references that are in the map. First posted on arXiv 7 Jun 2022.

Builds on

41 of 75 references.

References · 41

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  11. 2019Introduction to Online Convex Optimizationcited by 793
  12. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
29 more
  1. 2017The Implicit Bias of Gradient Descent on Separable Datacited by 649
  2. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  3. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  4. 2020Overfitting in adversarially robust deep learningcited by 504
  5. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  6. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  7. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  8. 2018Certified Defenses against Adversarial Examplescited by 305
  9. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  10. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  11. 2020Bag of Tricks for Adversarial Trainingcited by 199
  12. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  13. 2014A* Samplingcited by 150
  14. 2018Rademacher Complexity for Adversarially Robust Generalizationcited by 132
  15. 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
  16. 2018Adversarial examples from computational constraintscited by 79
  17. 2015Analysis of classifiers' robustness to adversarial perturbationscited by 76
  18. 2019Improving Adversarial Robustness of Ensembles with Diversity Trainingcited by 69
  19. 2016Kernel-based methods for bandit convex optimizationcited by 63
  20. 2020Informative Dropout for Robust Representation Learning: A Shape-bias Perspectivecited by 57
  21. 2020Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Frameworkcited by 45
  22. 2021On the Certified Robustness for Ensemble Models and Beyondcited by 40
  23. 2020Randomization matters. How to defend against strong adversarial attackscited by 37
  24. 2020Random Smoothing Might be Unable to Certify ℓ_∞ Robustness for High-Dimensional Imagescited by 35
  25. 2017Learning Deep ResNet Blocks Sequentially using Boosting Theorycited by 32
  26. 2019Online Non-Convex Learning: Following the Perturbed Leader is Optimalcited by 31
  27. 2020EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attackscited by 28
  28. 2018Functional Gradient Boosting based on Residual Network Perceptioncited by 14
  29. 2021A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustnesscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 6; 2024: 0; 2025: 1.

8 papers.

  1. 2022Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Gamescited by 8
  2. 2023On the Role of Randomization in Adversarially Robust Classificationcited by 4
  3. 2023On the Robustness of Randomized Ensembles to Adversarial Perturbationscited by 3
  4. 2023Adversarial attacks for mixtures of classifierscited by 1
  5. 2023Responsible AI (RAI) Games and Ensemblescited by 1
  6. 2023Local Boosting for Weakly-Supervised Learningcited by 0
  7. 2023Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgetscited by 0
  8. 2025Lattice Climber Attack: Adversarial attacks for randomized mixtures of classifierscited by 0