mlsanityData to 7 Oct 2026

A Minimax Approach Against Multi-Armed Adversarial Attacks Detection

arXiv 2302.02216 ↗First posted 4 Feb 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Multi-armed adversarial attacks, in which multiple algorithms and objective loss functions are simultaneously used at evaluation time, have been shown to be highly successful in fooling state-of-the-art adversarial examples detectors while requiring no specific side information about the detection mechanism. By formalizing the problem at hand, we can propose a solution that aggregates the soft-probability outputs of multiple pre-trained detectors according to a minimax approach. The proposed framework is mathematically sound, easy to implement, and modular, allowing for integrating existing or future detectors. Through extensive evaluation on popular datasets (e.g., CIFAR10 and SVHN), we show that our aggregation consistently outperforms individual state-of-the-art detectors against multi-armed adversarial attacks, making it an effective solution to improve the resilience of available methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 58 references that are in the map. First posted on arXiv 4 Feb 2023.

Builds on

46 of 58 references.

References · 46

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,296
34 more
  1. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  2. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  5. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  6. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  7. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  8. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  9. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  10. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  11. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  12. 2017Detecting Adversarial Samples from Artifactscited by 244
  13. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  14. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  15. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  16. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  17. 2020Smooth Adversarial Trainingcited by 89
  18. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  19. 2021DOCTOR: A Simple Method for Detecting Misclassification Errorscited by 52
  20. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  21. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  22. 2021Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Themcited by 46
  23. 2021Adversarial Robustness with Semi-Infinite Constrained Learningcited by 39
  24. 2020Selective Classification via One-Sided Predictioncited by 37
  25. 2021Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descentcited by 34
  26. 2020A General Framework For Detecting Anomalous Inputs to DNN Classifierscited by 24
  27. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22
  28. 2022Igeood: An Information Geometry Approach to Out-of-Distribution Detectioncited by 20
  29. 2021Adversarial Robustness via Fisher-Rao Regularizationcited by 19
  30. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
  31. 2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
  32. 2022Increasing Confidence in Adversarial Robustness Evaluationscited by 12
  33. 2022Randomized Smoothing under Attack: How Good is it in Pratice?cited by 7
  34. 2022MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectorscited by 2

Built on by

Not cited yet.