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

TL;DR

DeepFool is a straightforward and precise algorithm designed to generate minimal adversarial perturbations, enabling accurate assessment of deep neural networks' robustness against small, targeted image modifications.

Contribution

The paper introduces DeepFool, a novel method for efficiently computing adversarial perturbations to evaluate and improve neural network robustness.

Findings

DeepFool outperforms existing methods in generating adversarial examples.

It provides a reliable measure of classifier robustness.

Experimental results demonstrate its effectiveness on large-scale datasets.

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.