mlsanityData to 7 Oct 2026

Gradient-Based Adversarial and Out-of-Distribution Detection

arXiv 2206.08255 ↗First posted 16 Jun 2022cs.LG cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

We propose to utilize gradients for detecting adversarial and out-of-distribution samples. We introduce confounding labels -- labels that differ from normal labels seen during training -- in gradient generation to probe the effective expressivity of neural networks. Gradients depict the amount of change required for a model to properly represent given inputs, providing insight into the representational power of the model established by network architectural properties as well as training data. By introducing a label of different design, we remove the dependency on ground truth labels for gradient generation during inference. We show that our gradient-based approach allows for capturing the anomaly in inputs based on the effective expressivity of the models with no hyperparameter tuning or additional processing, and outperforms state-of-the-art methods for adversarial and out-of-distribution detection.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

37 of 45 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2017On Calibration of Modern Neural Networkscited by 4,860
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  11. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  12. 2016Adversarial examples in the physical worldcited by 1,762
25 more
  1. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  4. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  6. 2016An overview of gradient descent optimization algorithmscited by 1,021
  7. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  8. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  9. 2017Exploring Generalization in Deep Learningcited by 595
  10. 2016On the Expressive Power of Deep Neural Networkscited by 302
  11. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  12. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  13. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  14. 2020Gradients as a Measure of Uncertainty in Neural Networkscited by 55
  15. 2020Backpropagated Gradient Representations for Anomaly Detectioncited by 54
  16. 2017Between-class Learning for Image Classificationcited by 50
  17. 2018Classification Uncertainty of Deep Neural Networks Based on Gradient Informationcited by 43
  18. 2017CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognitioncited by 32
  19. 2020Contrastive Explanations in Neural Networkscited by 26
  20. 2018CURE-OR: Challenging Unreal and Real Environments for Object Recognitioncited by 18
  21. 2017On the Limitation of Convolutional Neural Networks in Recognizing Negative Imagescited by 17
  22. 2019Distorted Representation Space Characterization Through Backpropagated Gradientscited by 12
  23. 2021Extracting Causal Visual Features for Limited label Classificationcited by 12
  24. 2021PLM: Partial Label Masking for Imbalanced Multi-label Classificationcited by 10
  25. 2019Object Recognition under Multifarious Conditions: A Reliability Analysis and A Feature Similarity-based Performance Estimationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 4; 2025: 2; 2026: 1.

14 papers.

Sort:

  1. 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
  2. 2023Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentationcited by 11
  3. 2023Probing the Purview of Neural Networks via Gradient Analysiscited by 9
  4. 2023Low-Dimensional Gradient Helps Out-of-Distribution Detectioncited by 6
  5. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 5
  6. 2024Intelligent Multi-View Test Time Augmentationcited by 4
  7. 2024VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretabilitycited by 3
  8. 2022R2-AD2: Detecting Anomalies by Analysing the Raw Gradientcited by 2
  9. 2024Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networkscited by 2
  10. 2025GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detectioncited by 2
  11. 2023A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifierscited by 1
  12. 2024AnomalousPatchCore: Exploring the Use of Anomalous Samples in Industrial Anomaly Detectioncited by 1
2 more
  1. 2023GROOD: GRadient-Aware Out-of-Distribution Detectioncited by 0
  2. 2026HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classificationcited by 0