DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks

@article{MoosaviDezfooli2016DeepFoolAS,
  title={DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks},
  author={Seyed-Mohsen Moosavi-Dezfooli and Alhussein Fawzi and Pascal Frossard},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={2574-2582}
}
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… CONTINUE READING
Highly Influential
This paper has highly influenced 91 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 644 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 27 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 441 extracted citations

Adversarial Robustness Toolbox v0.2.2

View 12 Excerpts
Highly Influenced

Detecting Adversarial Examples Based on Steganalysis

ArXiv • 2018
View 6 Excerpts
Highly Influenced

Harmonic Adversarial Attack Method

View 13 Excerpts
Highly Influenced

645 Citations

02004002016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 645 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 19 references

Intriguing properties of neural networks

ArXiv • 2013
View 10 Excerpts
Highly Influenced

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction

IEEE/ACM Transactions on Computational Biology and Bioinformatics • 2015
View 1 Excerpt

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 1 Excerpt

Going deeper with convolutions

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 1 Excerpt

Similar Papers

Loading similar papers…