paper-with-me

홈 › Papers

DAmageNet: A Universal Adversarial Dataset

2019-12-16 · Sizhe Chen, Xiaolin Huang, Zhengbao He, Chengjin Sun

It is now well known that deep neural networks (DNNs) are vulnerable to adversarial attack. Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence. But most of the existing adversarial attacks have high success rate only when the information of the attacked DNN is well-known or could be estimated by massive queries. A promising way is to generate adversarial samples with high transferability. By this way, we generate 96020 transferable adversarial samples from original ones in ImageNet. The average difference, measured by root means squared deviation, is only around 3.8 on average. However, the adversarial samples are misclassified by various models with an error rate up to 90\%. Since the images are generated independently with the attacked DNNs, this is essentially zero-query adversarial attack. We call the dataset \emph{DAmageNet}, which is the first universal adversarial dataset that beats many models trained in ImageNet. By finding the drawbacks, DAmageNet could serve as a benchmark to study and improve robustness of DNNs. DAmageNet could be downloaded in http://www.pami.sjtu.edu.cn/Show/56/122.

📄 PDF Abstract BibTeX arXiv:1912.07160

Code (1)

XingLiangLondon/Image-Similarity-in-Percentage

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet

2020-01-16 · Sizhe Chen, Zhengbao He, Chengjin Sun, Jie Yang 외

Adversarial attacks on deep neural networks (DNNs) have been found for several years. However, the existing adversarial attacks have high success rates only when the information of the victim DNN is well-known or could b…

Adversarial Attack

FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features

2025-12-03 · Zhigang Yang, Yuan Liu, Jiawei Zhang, Puning Zhang 외 arxiv

Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poo…

Computational EfficiencyImage ClassificationAdversarial Defense

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 …

Graph Classification

Universal Adversarial Attack on Deep Learning Based Prognostics

2021-09-15 · Arghya Basak, Pradeep Rathore, Sri Harsha Nistala, Sagar Srinivas 외

Deep learning-based time series models are being extensively utilized in engineering and manufacturing industries for process control and optimization, asset monitoring, diagnostic and predictive maintenance. These model…

Adversarial AttackDeep LearningDiagnosticregression+3

Generalizing Universal Adversarial Attacks Beyond Additive Perturbations

2020-10-15 · Yanghao Zhang, Wenjie Ruan, Fu Wang, Xiaowei Huang

The previous study has shown that universal adversarial attacks can fool deep neural networks over a large set of input images with a single human-invisible perturbation. However, current methods for universal adversaria…

Adversarial Attack