mlsanityData to 7 Oct 2026

A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness

arXiv 2103.01276 ↗First posted 1 Mar 2021cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Alongside the well-publicized accomplishments of deep neural networks there has emerged an apparent bug in their success on tasks such as object recognition: with deep models trained using vanilla methods, input images can be slightly corrupted in order to modify output predictions, even when these corruptions are practically invisible. This apparent lack of robustness has led researchers to propose methods that can help to prevent an adversary from having such capabilities. The state-of-the-art approaches have incorporated the robustness requirement into the loss function, and the training process involves taking stochastic gradient descent steps not using original inputs but on adversarially-corrupted ones. In this paper we propose a multiclass boosting framework to ensure adversarial robustness. Boosting algorithms are generally well-suited for adversarial scenarios, as they were classically designed to satisfy a minimax guarantee. We provide a theoretical foundation for this methodology and describe conditions under which robustness can be achieved given a weak training oracle. We show empirically that adversarially-robust multiclass boosting not only outperforms the state-of-the-art methods, it does so at a fraction of the training time.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 1 Mar 2021.

Builds on

32 of 43 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  11. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  12. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
20 more
  1. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  2. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  3. 2019Adversarial Training for Free!cited by 638
  4. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  5. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  6. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  7. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  8. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  9. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  10. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  11. 2018Certified Defenses against Adversarial Examplescited by 305
  12. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  13. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  14. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  15. 2018Motivating the Rules of the Game for Adversarial Example Researchcited by 57
  16. 2019An Alternative Surrogate Loss for PGD-based Adversarial Testingcited by 45
  17. 2020Reducing Adversarially Robust Learning to Non-Robust PAC Learningcited by 28
  18. 2019Provably Robust Boosted Decision Stumps and Trees against Adversarial Attackscited by 26
  19. 2017Attacking the Madry Defense Model with L1-based Adversarial Examplescited by 21
  20. 2019On Robustness to Adversarial Examples and Polynomial Optimizationcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 1.

6 papers.

  1. 2022Building Robust Ensembles via Margin Boostingcited by 8
  2. 2023The Impossibility of Parallelizing Boostingcited by 7
  3. 2022Boosting Barely Robust Learners: A New Perspective on Adversarial Robustnesscited by 3
  4. 2022Online Agnostic Multiclass Boostingcited by 3
  5. 2023On the Robustness of Randomized Ensembles to Adversarial Perturbationscited by 3
  6. 2024The Cost of Parallelizing Boostingcited by 3