DeepFool: a simple and accurate method to fool deep neural networks. State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images. Despite the importance of this phenomenon, no effective methods have been proposed to accurately compute the robustness of state-of-the-art deep classifiers to such perturbations on large-scale datasets. In this paper, we fill this gap and propose the DeepFool algorithm to efficiently compute perturbations that fool deep networks, and thus reliably quantify the robustness of these classifiers. Extensive experimental results show that our approach outperforms recent methods in the task of computing adversarial perturbations and making classifiers more robust. DeepFool: a simple and accurate method to fool deep neural networks.
Keywords for this software
References in zbMATH (referenced in 4 articles )
Showing results 1 to 4 of 4.
- Benning, Martin; Celledoni, Elena; Ehrhardt, Matthias J.; Owren, Brynjulf; Schönlieb, Carola-Bibiane: Deep learning as optimal control problems: models and numerical methods (2019)
- Dreossi, Tommaso; Donzé, Alexandre; Seshia, Sanjit A.: Compositional falsification of Cyber-physical systems with machine learning components (2019)
- Fawzi, Alhussein; Fawzi, Omar; Frossard, Pascal: Analysis of classifiers’ robustness to adversarial perturbations (2018)
- Jonas Rauber, Wieland Brendel, Matthias Bethge: Foolbox v0.8.0: A Python toolbox to benchmark the robustness of machine learning models (2017) arXiv