paper-with-me

Papers

Learning Universal Adversarial Perturbations with Generative Models

2017-08-17 · Jamie Hayes, George Danezis

Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that given a dataset and classifier, there exists so called universal adversarial perturbations, a single perturbation that causes a misclassification when applied to any input. In this work, we introduce universal adversarial networks, a generative network that is capable of fooling a target classifier when it's generated output is added to a clean sample from a dataset. We show that this technique improves on known universal adversarial attacks.

📄 PDF Abstract BibTeX arXiv:1708.05207

Code (1)

jhayes14/UAN 공식 구현 pytorch

Tasks

Graph Classification

Similar Papers 제목 키워드 기반

Enabling Fast and Universal Audio Adversarial Attack Using Generative Model

2020-04-26 · Yi Xie, Zhuohang Li, Cong Shi, Jian Liu 외

Recently, the vulnerability of DNN-based audio systems to adversarial attacks has obtained the increasing attention. However, the existing audio adversarial attacks allow the adversary to possess the entire user's audio …

Adversarial Attack

Universal Adversarial Perturbations Generative Network for Speaker Recognition

2020-04-07 · Jiguo Li, Xinfeng Zhang, Chuanmin Jia, Jizheng Xu 외

Attacking deep learning based biometric systems has drawn more and more attention with the wide deployment of fingerprint/face/speaker recognition systems, given the fact that the neural networks are vulnerable to the ad…

Speaker Recognition

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