How to Manipulate CNNs to Make Them Lie: the GradCAM Case
Abstract
Recently many methods have been introduced to explain CNN decisions. However, it has been shown that some methods can be sensitive to manipulation of the input. We continue this line of work and investigate the explanation method GradCAM. Instead of manipulating the input, we consider an adversary that manipulates the model itself to attack the explanation. By changing weights and architecture, we demonstrate that it is possible to generate any desired explanation, while leaving the model's accuracy essentially unchanged. This illustrates that GradCAM cannot explain the decision of every CNN and provides a proof of concept showing that it is possible to obfuscate the inner workings of a CNN. Finally, we combine input and model manipulation. To this end we put a backdoor in the network: the explanation is correct unless there is a specific pattern present in the input, which triggers a malicious explanation. Our work raises new security concerns, especially in settings where explanations of models may be used to make decisions, such as in the medical domain.
Cite
@article{arxiv.1907.10901,
title = {How to Manipulate CNNs to Make Them Lie: the GradCAM Case},
author = {Tom Viering and Ziqi Wang and Marco Loog and Elmar Eisemann},
journal= {arXiv preprint arXiv:1907.10901},
year = {2019}
}
Comments
Presented at BMVC 2019: Workshop on Interpretable and Explainable Machine Vision, Cardiff, UK. Updated to BMVC template