mlsanityData to 14 Oct 2026

Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets

arXiv 2306.15482 ↗First posted 27 Jun 2023cs.AI cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite incredible advances, deep learning has been shown to be susceptible to adversarial attacks. Numerous approaches have been proposed to train robust networks both empirically and certifiably. However, most of them defend against only a single type of attack, while recent work takes steps forward in defending against multiple attacks. In this paper, to understand multi-target robustness, we view this problem as a bargaining game in which different players (adversaries) negotiate to reach an agreement on a joint direction of parameter updating. We identify a phenomenon named player domination in the bargaining game, namely that the existing max-based approaches, such as MAX and MSD, do not converge. Based on our theoretical analysis, we design a novel framework that adjusts the budgets of different adversaries to avoid any player dominance. Experiments on standard benchmarks show that employing the proposed framework to the existing approaches significantly advances multi-target robustness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 59 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

44 of 59 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  12. 2018Robustness May Be at Odds with Accuracycited by 880
32 more
  1. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  2. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  3. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  4. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  5. 2018Certified Defenses against Adversarial Examplescited by 306
  6. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  7. 2018A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decaycited by 226
  8. 2018Adversarial Logit Pairingcited by 224
  9. 2020Bag of Tricks for Adversarial Trainingcited by 200
  10. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 183
  11. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
  12. 2018Are adversarial examples inevitable?cited by 113
  13. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  14. 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
  15. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  16. 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
  17. 2017Exploring the Landscape of Spatial Robustnesscited by 81
  18. 2020Informative Dropout for Robust Representation Learning: A Shape-bias Perspectivecited by 57
  19. 2021Probabilistic Margins for Instance Reweighting in Adversarial Trainingcited by 57
  20. 2019Efficient Adversarial Training with Transferable Adversarial Examplescited by 56
  21. 2019Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attackscited by 54
  22. 2020Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Freecited by 48
  23. 2019Accurate, reliable and fast robustness evaluationcited by 43
  24. 2019Provable robustness against all adversarial lp-perturbations for p≥ 1cited by 39
  25. 2022Self-Ensemble Adversarial Training for Improved Robustnesscited by 38
  26. 2018Logit Pairing Methods Can Fool Gradient-Based Attackscited by 27
  27. 2021Class-Aware Robust Adversarial Training for Object Detectioncited by 27
  28. 2019Transfer of Adversarial Robustness Between Perturbation Typescited by 25
  29. 2022Adversarial Weight Perturbation Improves Generalization in Graph Neural Networkscited by 21
  30. 2022RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrievalcited by 15
  31. 2022Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attackcited by 13
  32. 2022Building Robust Ensembles via Margin Boostingcited by 8

Built on by

Not cited yet.