Inspecting adversarial examples using the Fisher information
Not on the map. Why?
Abstract (arXiv)
Adversarial examples are slight perturbations that are designed to fool artificial neural networks when fed as an input. In this work the usability of the Fisher information for the detection of such adversarial attacks is studied. We discuss various quantities whose computation scales well with the network size, study their behavior on adversarial examples and show how they can highlight the importance of single input neurons, thereby providing a visual tool for further analyzing (un-)reasonable behavior of a neural network. The potential of our methods is demonstrated by applications to the MNIST, CIFAR10 and Fruits-360 datasets.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Sep 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 3; 2023: 0; 2024: 1; 2025: 0; 2026: 1.
7 papers.
- 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
- 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
- 2022On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similaritycited by 4
- 2022Adversarial robustness of VAEs through the lens of local geometrycited by 4
- 2021Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimizationcited by 3
- 2024Cartan moving frames and the data manifoldscited by 1
- 2026Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithmscited by 1
- 2026Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms3 Jun 2026
- 2024Cartan moving frames and the data manifolds18 Sep 2024
- 2022Adversarial robustness of VAEs through the lens of local geometry8 Aug 2022
- 2022On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity25 May 2022
- 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons19 Jan 2022
- 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS14 Feb 2021
- 2021Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization19 Jan 2021