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

arXiv: https://arxiv.org/abs/2004.09179 · HTML: https://mlsanity.com/paper/2004.09179/

## Key facts

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

## Built on by (most cited first, 18 of 18)

- [Adversarial Example Detection for DNN Models: A Review and Experimental Comparison](https://mlsanity.com/paper/2105.00203/) (2021)
- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs](https://mlsanity.com/paper/2203.07808/) (2022)
- [Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey](https://mlsanity.com/paper/2205.08099/) (2022)
- [Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection](https://mlsanity.com/paper/2405.17816/) (2024)
- [CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning](https://mlsanity.com/paper/2210.01742/) (2022)
- [Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection](https://mlsanity.com/paper/2103.05354/) (2021)
- [Low-Dimensional Gradient Helps Out-of-Distribution Detection](https://mlsanity.com/paper/2310.17163/) (2023)
- [Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors](https://mlsanity.com/paper/2404.12120/) (2024)
- [Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection](https://mlsanity.com/paper/2308.11480/) (2023)
- [CorrGAN: Input Transformation Technique Against Natural Corruptions](https://mlsanity.com/paper/2204.08623/) (2022)
- [R2-AD2: Detecting Anomalies by Analysing the Raw Gradient](https://mlsanity.com/paper/2206.10259/) (2022)
- [Deep Neural Networks with Efficient Guaranteed Invariances](https://mlsanity.com/paper/2303.01567/) (2023)
- [Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images](https://mlsanity.com/paper/2310.13782/) (2023)
- [XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection](https://mlsanity.com/paper/2210.11590/) (2022)
- [Constraining Representations Yields Models That Know What They Don't Know](https://mlsanity.com/paper/2208.14488/) (2022)
- [AdvCheck: Characterizing Adversarial Examples via Local Gradient Checking](https://mlsanity.com/paper/2303.18131/) (2023)
- [GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations](https://mlsanity.com/paper/2307.02672/) (2023)

## 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.