DeepFool: a simple and accurate method to fool deep neural networks

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal Frossard
11/14/2015
cs.LGcs.CV

Official code: LTS4/DeepFool (362 stars, last commit 2020-03-31).

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.

View on arXivView PDF

Code Implementations(1)

LTS4/DeepFoolOfficial100%

A simple and accurate method to fool deep neural networks

362129MATLAB, PythonNov 23, 20156 years ago

Similar Papers

Universal adversarial perturbations

90% match1 repo2512016

Exploring the Space of Adversarial Images

88% match1 repo702015

Feature compression is the root cause of adversarial fragility in neural network classifiers

87% match2024

A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking

86% match2023

Towards Class-wise Robustness Analysis

86% match2024

DeepConsensus: using the consensus of features from multiple layers to attain robust image classification

86% match2018

Cite this paper

@article{moosavidezfooli2015deepfool,
  title  = {DeepFool: a simple and accurate method to fool deep neural networks},
  author = {Seyed-Mohsen Moosavi-Dezfooli and Alhussein Fawzi and Pascal Frossard},
  year   = {2015},
  eprint = {1511.04599},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1511.04599}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1511.04599.svg)](https://codeofpaper.com/paper/1511.04599)

Discussion