mlsanityData to 14 Oct 2026

GraN: An Efficient Gradient-Norm Based Detector for Adversarial and Misclassified Examples

arXiv 2004.09179 ↗First posted 20 Apr 2020cs.LG cs.CR cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are vulnerable to adversarial examples and other data perturbations. Especially in safety critical applications of DNNs, it is therefore crucial to detect misclassified samples. The current state-of-the-art detection methods require either significantly more runtime or more parameters than the original network itself. This paper therefore proposes GraN, a time- and parameter-efficient method that is easily adaptable to any DNN. GraN is based on the layer-wise norm of the DNN's gradient regarding the loss of the current input-output combination, which can be computed via backpropagation. GraN achieves state-of-the-art performance on numerous problem set-ups.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 7; 2023: 6; 2024: 2.

18 papers.

Sort:

By area:

  1. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  2. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 39
  3. 2022Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNscited by 16
  4. 2022Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Surveycited by 12
  5. 2024Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detectioncited by 12
  6. 2022CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learningcited by 11
  7. 2021Revisiting Model's Uncertainty and Confidences for Adversarial Example Detectioncited by 9
  8. 2023Low-Dimensional Gradient Helps Out-of-Distribution Detectioncited by 6
  9. 2024Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectorscited by 4
  10. 2023Expecting The Unexpected: Towards Broad Out-Of-Distribution Detectioncited by 3
  11. 2022CorrGAN: Input Transformation Technique Against Natural Corruptionscited by 2
  12. 2022R2-AD2: Detecting Anomalies by Analysing the Raw Gradientcited by 2
6 more
  1. 2023Deep Neural Networks with Efficient Guaranteed Invariancescited by 2
  2. 2023Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Imagescited by 2
  3. 2022XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detectioncited by 1
  4. 2022Constraining Representations Yields Models That Know What They Don't Knowcited by 0
  5. 2023AdvCheck: Characterizing Adversarial Examples via Local Gradient Checkingcited by 0
  6. 2023GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformationscited by 0