mlsanityData to 7 Oct 2026

Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning

arXiv 2211.14669 ↗First posted 26 Nov 2022cs.LG cs.AI cs.GTcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defenses include Barrage of Random Transforms (BaRT), Friendly Adversarial Training (FAT), Trash is Treasure (TiT) and ensemble models made up of Vision Transformers (ViTs), Big Transfer models and Spiking Neural Networks (SNNs). We first conduct a transferability analysis, to demonstrate the adversarial examples generated by customized attacks on one defense, are not often misclassified by another defense. This finding leads to two important questions. First, how can the low transferability between defenses be utilized in a game theoretic framework to improve the robustness? Second, how can an adversary within this framework develop effective multi-model attacks? In this paper, we provide a game-theoretic framework for ensemble adversarial attacks and defenses. Our framework is called Game theoretic Mixed Experts (GaME). It is designed to find the Mixed-Nash strategy for both a detector based and standard defender, when facing an attacker employing compositional adversarial attacks. We further propose three new attack algorithms, specifically designed to target defenses with randomized transformations, multi-model voting schemes, and adversarial detector architectures. These attacks serve to both strengthen defenses generated by the GaME framework and verify their robustness against unforeseen attacks. Overall, our framework and analyses advance the field of adversarial machine learning by yielding new insights into compositional attack and defense formulations.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 55 references that are in the map. First posted on arXiv 26 Nov 2022.

Builds on

38 of 55 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  11. 2020Quantifying Attention Flow in Transformerscited by 759
  12. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
26 more
  1. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  2. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  3. 2019On Evaluating Adversarial Robustnesscited by 442
  4. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  5. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  6. 2018Adversarially Robust Generalization Requires More Datacited by 318
  7. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  8. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  9. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  10. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  11. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  12. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  13. 2022Guided Diffusion Model for Adversarial Purificationcited by 90
  14. 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
  15. 2020Randomization matters. How to defend against strong adversarial attackscited by 37
  16. 2019Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forwardcited by 33
  17. 2021Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attackscited by 24
  18. 2021Mixed Nash Equilibria in the Adversarial Examples Gamecited by 22
  19. 2020A Game Theoretic Analysis of Additive Adversarial Attacks and Defensescited by 21
  20. 2022Demystifying the Adversarial Robustness of Random Transformation Defensescited by 14
  21. 2017MTDeep: Boosting the Security of Deep Neural Nets Against Adversarial Attacks with Moving Target Defensecited by 12
  22. 2022Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examplescited by 12
  23. 2020Beware the Black-Box: on the Robustness of Recent Defenses to Adversarial Examplescited by 11
  24. 2020Advocating for Multiple Defense Strategies against Adversarial Examplescited by 11
  25. 2019One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examplescited by 8
  26. 2022Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Gamescited by 8

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 2.

6 papers.

  1. 2023PubDef: Defending Against Transfer Attacks From Public Modelscited by 7
  2. 2024The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggerscited by 3
  3. 2024Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustnesscited by 2
  4. 2023Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learningcited by 1
  5. 2025Busting the Paper Ballot: Voting Meets Adversarial Machine Learningcited by 1
  6. 2025On the Trade-Off Between Transparency and Security in Adversarial Machine Learningcited by 0