mlsanityData to 7 Oct 2026

ML-LOO: Detecting Adversarial Examples with Feature Attribution

arXiv 1906.03499 ↗First posted 8 Jun 2019cs.LG cs.CR stat.MLcited by 48

Not on the map. Why?

Abstract (arXiv)

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a significant difference in feature attributions of adversarially crafted examples from those of original ones. Based on this observation, we introduce a new framework to detect adversarial examples through thresholding a scale estimate of feature attribution scores. Furthermore, we extend our method to include multi-layer feature attributions in order to tackle the attacks with mixed confidence levels. Through vast experiments, our method achieves superior performances in distinguishing adversarial examples from popular attack methods on a variety of real data sets among state-of-the-art detection methods. In particular, our method is able to detect adversarial examples of mixed confidence levels, and transfer between different attacking methods.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 9; 2023: 6; 2024: 9; 2025: 6; 2026: 1.

48 papers.

Sort:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2023Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarkingcited by 37
  3. 2022Visual Prompting for Adversarial Robustnesscited by 33
  4. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  5. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  6. 2022Reverse Engineering of Imperceptible Adversarial Image Perturbationscited by 17
  7. 2021SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluationcited by 16
  8. 2021A Game-Theoretic Taxonomy of Visual Concepts in DNNscited by 16
  9. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
  10. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  11. 2022Increasing Confidence in Adversarial Robustness Evaluationscited by 12
  12. 2021PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testingcited by 11
36 more
  1. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
  2. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  3. 2021Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learningcited by 7
  4. 2022SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usabilitycited by 7
  5. 2024LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributionscited by 5
  6. 2024Towards Robust Vision Transformer via Masked Adaptive Ensemblecited by 4
  7. 2022Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attackscited by 3
  8. 2024Trustworthy Actionable Perturbationscited by 3
  9. 2021Adversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attackscited by 2
  10. 2021BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidabilitycited by 2
  11. 2021Adversarial Examples Detection with Bayesian Neural Networkcited by 2
  12. 2021Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Featurescited by 2
  13. 2022Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problemcited by 2
  14. 2023Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizercited by 2
  15. 2024PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysiscited by 2
  16. 2024ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformercited by 2
  17. 2021Benford's law: what does it say on adversarial images?cited by 1
  18. 2023Can Adversarial Examples Be Parsed to Reveal Victim Model Information?cited by 1
  19. 2023X-Detect: Explainable Adversarial Patch Detection for Object Detectors in Retailcited by 1
  20. 2024Low-Quality Image Detection by Hierarchical VAEcited by 1
  21. 2025Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attackscited by 1
  22. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 0
  23. 2021Segmentation Fault: A Cheap Defense Against Adversarial Machine Learningcited by 0
  24. 2022Adversarial Detector with Robust Classifiercited by 0
  25. 2022Adversarial Patterns: Building Robust Android Malware Classifierscited by 0
  26. 2022Adversarial Example Detection in Deployed Tree Ensemblescited by 0
  27. 2023AdvCheck: Characterizing Adversarial Examples via Local Gradient Checkingcited by 0
  28. 2024Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluationcited by 0
  29. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
  30. 2024Towards Calibrated Losses for Adversarial Robust Reject Option Classificationcited by 0
  31. 2025Enhancing Adversarial Example Detection Through Model Explanationcited by 0
  32. 2025Smaller is Better: Enhancing Transparency in Vehicle AI Systems via Pruningcited by 0
  33. 2025Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AIcited by 0
  34. 2025Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustnesscited by 0
  35. 2025Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defensescited by 0
  36. 2026What Helps---and What Hurts: Bidirectional Explanations for Vision Transformerscited by 0