paper-with-me

Papers

Universal adversarial perturbations

2016-10-26 · CVPR 2017 7 · Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard

Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible to the human eye. We further empirically analyze these universal perturbations and show, in particular, that they generalize very well across neural networks. The surprising existence of universal perturbations reveals important geometric correlations among the high-dimensional decision boundary of classifiers. It further outlines potential security breaches with the existence of single directions in the input space that adversaries can possibly exploit to break a classifier on most natural images.

📄 PDF Abstract BibTeX arXiv:1610.08401

Code (8)

LTS4/universal 공식 구현 tf
BXuan694/Universal-Adversarial-Perturbation pytorch
BXuan694/universalAdversarialPerturbation pytorch
NetoPedro/Universal-Adversarial-Perturbations-Pytorch pytorch
bingcheng45/hnr-extension tf
ferjad/Universal_Adverserial_Perturbation_pytorch pytorch
riiswa/universal pytorch
ssg-research/flare pytorch

Similar Papers 제목 키워드 기반

Defending Against Universal Perturbations With Shared Adversarial Training

2018-12-10 · ICCV 2019 10 · Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image class…

image-classificationImage ClassificationSemantic Segmentation

On Distinctive Properties of Universal Perturbations

2021-12-31 · Sung Min Park, Kuo-An Wei, Kai Xiao, Jerry Li 외

We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generated by projected gradient descent exhibit…

Universal Adversarial Perturbation for Text Classification

2019-10-10 · Hang Gao, Tim Oates

Given a state-of-the-art deep neural network text classifier, we show the existence of a universal and very small perturbation vector (in the embedding space) that causes natural text to be misclassified with high probab…

Adversarial TextClassificationGeneral Classificationtext-classification+1

Universal Adversarial Perturbations: Efficiency on a small image dataset

2022-10-10 · Waris Radji

Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has show…

image-classificationImage Classification

Double Targeted Universal Adversarial Perturbations

2020-10-07 · Philipp Benz, Chaoning Zhang, Tooba Imtiaz, In So Kweon

Despite their impressive performance, deep neural networks (DNNs) are widely known to be vulnerable to adversarial attacks, which makes it challenging for them to be deployed in security-sensitive applications, such as a…

Autonomous Driving