A Vulnerability of Attribution Methods Using Pre-Softmax Scores
Not on the map. Why?
Abstract (arXiv)
We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is known that this type of networks are vulnerable to adversarial attacks, in which imperceptible perturbations of the input may alter the outputs of the model. In contrast, here we focus on effects that small modifications in the model may cause on the attribution method without altering the model outputs.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 16 references that are in the map. First posted on arXiv 6 Jul 2023.
Builds on
14 of 16 references.
References · 14
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
- 2017Interpretation of Neural Networks is Fragilecited by 444
- 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
- 2020A Survey on the Explainability of Supervised Machine Learningcited by 227
- 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
- 2019Fooling Neural Network Interpretations via Adversarial Model Manipulationcited by 112
- 2015Analyzing Classifiers: Fisher Vectors and Deep Neural Networkscited by 24
Built on by
Not cited yet.