mlsanityData to 7 Oct 2026

Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

arXiv 2103.04302 ↗First posted 7 Mar 2021cs.LG cs.CR cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs), which are maliciously designed to cause dramatic model output errors. In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations. This phenomenon motivates us to design another classifier (called dual classifier) with transformed decision boundary, which can be collaboratively used with the original classifier (called primal classifier) to detect AEs, by virtue of the sensitivity inconsistency. When comparing with the state-of-the-art algorithms based on Local Intrinsic Dimensionality (LID), Mahalanobis Distance (MD), and Feature Squeezing (FS), our proposed Sensitivity Inconsistency Detector (SID) achieves improved AE detection performance and superior generalization capabilities, especially in the challenging cases where the adversarial perturbation levels are small. Intensive experimental results on ResNet and VGG validate the superiority of the proposed SID.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 7 Mar 2021.

Builds on

37 of 51 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Adversarial examples in the physical worldcited by 1,762
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2018Robustness May Be at Odds with Accuracycited by 873
  8. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  9. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  10. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  11. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  12. 2017Adversarial Patchcited by 514
25 more
  1. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  2. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  3. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  4. 2018Adversarially Robust Generalization Requires More Datacited by 318
  5. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  6. 2017Detecting Adversarial Samples from Artifactscited by 244
  7. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  8. 2017On Detecting Adversarial Perturbationscited by 232
  9. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  10. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  11. 2017The Space of Transferable Adversarial Examplescited by 156
  12. 2019Adversarial Training Can Hurt Generalizationcited by 131
  13. 2018Curriculum Adversarial Trainingcited by 89
  14. 2016Robustness of classifiers: from adversarial to random noisecited by 87
  15. 2018Adversarial vulnerability for any classifiercited by 78
  16. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  17. 2018On the Suitability of Lp-norms for Creating and Preventing Adversarial Examplescited by 57
  18. 2017Defense against Universal Adversarial Perturbationscited by 48
  19. 2018Classification Uncertainty of Deep Neural Networks Based on Gradient Informationcited by 43
  20. 2018Detection based Defense against Adversarial Examples from the Steganalysis Point of Viewcited by 32
  21. 2019DLA: Dense-Layer-Analysis for Adversarial Example Detectioncited by 20
  22. 2019Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspectioncited by 16
  23. 2017Robustness of classifiers to universal perturbations: a geometric perspectivecited by 14
  24. 2019Intrinsic dimension estimation for locally undersampled datacited by 10
  25. 2018A Geometric Perspective on the Transferability of Adversarial Directionscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 6; 2024: 7; 2025: 4; 2026: 2.

29 papers.

Sort:

By area:

  1. 2021Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descentcited by 34
  2. 2022Detecting Adversarial Perturbations in Multi-Task Perceptioncited by 15
  3. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  4. 2022What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradictioncited by 10
  5. 2023Improving the Robustness of Transformer-based Large Language Models with Dynamic Attentioncited by 10
  6. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  7. 2021Self-Supervised Adversarial Example Detection by Disentangled Representationcited by 7
  8. 2022Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learningcited by 5
  9. 2023Detecting Adversarial Faces Using Only Real Face Self-Perturbationscited by 4
  10. 2024Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectorscited by 4
  11. 2021Anomaly Detection of Adversarial Examples using Class-conditional Generative Adversarial Networkscited by 3
  12. 2022Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attackscited by 3
17 more
  1. 2024Privacy-preserving Universal Adversarial Defense for Black-box Modelscited by 3
  2. 2024DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domaincited by 2
  3. 2025FlowPure: Continuous Normalizing Flows for Adversarial Purificationcited by 2
  4. 2021GGT: Graph-Guided Testing for Adversarial Sample Detection of Deep Neural Networkcited by 1
  5. 2023Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalizationcited by 1
  6. 2023Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Methodcited by 1
  7. 2024Understanding the Robustness of Graph Neural Networks against Adversarial Attackscited by 1
  8. 2025A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detectioncited by 1
  9. 2022Adversarial Example Detection in Deployed Tree Ensemblescited by 0
  10. 2023Adversarial defense based on distribution transfercited by 0
  11. 2024AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptationcited by 0
  12. 2024Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noisescited by 0
  13. 2024Adversarial Detection with a Dynamically Stable Systemcited by 0
  14. 2025TRAIL: Transferable Robust Adversarial Images via Latent diffusioncited by 0
  15. 2025FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Featurescited by 0
  16. 2026GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attackscited by 0
  17. 2026Multi-Task Consistency-based Detection of Adversarial Attackscited by 0