mlsanityData to 7 Oct 2026

Adversarial Sample Detection Through Neural Network Transport Dynamics

arXiv 2306.04252 ↗First posted 7 Jun 2023cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose a detector of adversarial samples that is based on the view of neural networks as discrete dynamic systems. The detector tells clean inputs from abnormal ones by comparing the discrete vector fields they follow through the layers. We also show that regularizing this vector field during training makes the network more regular on the data distribution's support, thus making the activations of clean inputs more distinguishable from those of abnormal ones. Experimentally, we compare our detector favorably to other detectors on seen and unseen attacks, and show that the regularization of the network's dynamics improves the performance of adversarial detectors that use the internal embeddings as inputs, while also improving test accuracy.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 50 of its 63 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

50 of 63 references.

References · 50

  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. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2016Wide Residual Networkscited by 3,057
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2016Identity Mappings in Deep Residual Networkscited by 1,960
38 more
  1. 2016Adversarial examples in the physical worldcited by 1,762
  2. 2016Concrete Problems in AI Safetycited by 1,582
  3. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  6. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  7. 2016Universal adversarial perturbationscited by 774
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  9. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  10. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  11. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  12. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
  13. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  14. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  15. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  16. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  17. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  18. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  19. 2017Detecting Adversarial Samples from Artifactscited by 244
  20. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  21. 2017On Detecting Adversarial Perturbationscited by 232
  22. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  23. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  24. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
  25. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
  26. 2020Lipschitz constant estimation of Neural Networks via sparse polynomial optimizationcited by 87
  27. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  28. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  29. 2018Limitations of the Lipschitz constant as a defense against adversarial examplescited by 48
  30. 2015Evasion and Hardening of Tree Ensemble Classifierscited by 44
  31. 2018On the Geometry of Adversarial Examplescited by 43
  32. 2021SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domaincited by 30
  33. 2021LipBaB: Computing exact Lipschitz constant of ReLU networkscited by 16
  34. 2019Towards Robust ResNet: A Small Step but A Giant Leapcited by 15
  35. 2020An Efficient Adversarial Attack for Tree Ensemblescited by 9
  36. 2020A Principle of Least Action for the Training of Neural Networkscited by 8
  37. 2020The Dilemma Between Data Transformations and Adversarial Robustness for Time Series Application Systemscited by 6
  38. 2021Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoisingcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Are classical deep neural networks weakly adversarially robust?cited by 0