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 pr...

Full description

Saved in:
Bibliographic Details
Published in:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2574 - 2582
Main Authors: Moosavi-Dezfooli, Seyed-Mohsen, Fawzi, Alhussein, Frossard, Pascal
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2016
Subjects:
Algorithm design and analysis
Computer vision
Level set
Neural networks
Optimization
Pattern recognition
Robustness
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.282