most citedTransferability of Adversarial Examples to Attack Cloud-based Image Classifier Service

11 citations · 22 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG20206 cited

Attacking and Defending Machine Learning Applications of Public Cloud

Dou Goodman, Hao Xin

Adversarial attack breaks the boundaries of traditional security defense. For adversarial attack and the characteristics of cloud services, we propose Security Development Lifecycl…

cs.CL20205 cited

FastWordBug: A Fast Method To Generate Adversarial Text Against NLP Applications

Dou Goodman, Lv Zhonghou, Wang minghua

In this paper, we present a novel algorithm, FastWordBug, to efficiently generate small text perturbations in a black-box setting that forces a sentiment analysis or text classific…

cs.CV202011 cited

Transferability of Adversarial Examples to Attack Cloud-based Image Classifier Service

Dou Goodman

In recent years, Deep Learning(DL) techniques have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported t…

cs.LG2020

Advbox: a toolbox to generate adversarial examples that fool neural networks

Dou Goodman, Hao Xin, Wang Yang +3

In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or…

cs.CV2019

Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield

Dou Goodman, Tao Wei

Many recent works demonstrated that Deep Learning models are vulnerable to adversarial examples.Fortunately, generating adversarial examples usually requires white-box access to th…