DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Top Cited Papers
- 12 December 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2574-2582
- https://doi.org/10.1109/cvpr.2016.282
Abstract
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.1Keywords
Other Versions
This publication has 14 references indexed in Scilit:
- What Is Holding Back Convnets for Detection?Published by Springer Science and Business Media LLC ,2015
- MatConvNetPublished by Association for Computing Machinery (ACM) ,2015
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Going deeper with convolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- A Deep Learning Network Approach to ab initio Protein Secondary Structure PredictionIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2015
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- Deep autoencoder neural networks for gene ontology annotation predictionsPublished by Association for Computing Machinery (ACM) ,2014
- Strategies for training large scale neural network language modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Object Recognition with Gradient-Based LearningPublished by Springer Science and Business Media LLC ,1999
- Least-Change Secant Update Methods for Underdetermined SystemsSIAM Journal on Numerical Analysis, 1990