activity
20172019
most citedDeceiving Google's Perspective API Built for Detecting Toxic Comments

134 citations · 234 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG2019

Are Odds Really Odd? Bypassing Statistical Detection of Adversarial Examples

Hossein Hosseini, Sreeram Kannan, Radha Poovendran

Deep learning classifiers are known to be vulnerable to adversarial examples. A recent paper presented at ICML 2019 proposed a statistical test detection method based on the observ…

cs.LG2019

Dropping Pixels for Adversarial Robustness

Hossein Hosseini, Sreeram Kannan, Radha Poovendran

Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We…

cs.CV2018

Assessing Shape Bias Property of Convolutional Neural Networks

Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal +1

It is known that humans display "shape bias" when classifying new items, i.e., they prefer to categorize objects based on their shape rather than color. Convolutional Neural Networ…

cs.CV2018

Semantic Adversarial Examples

Hossein Hosseini, Radha Poovendran

Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mos…

cs.MM20179 cited

Attacking Automatic Video Analysis Algorithms: A Case Study of Google Cloud Video Intelligence API

Hossein Hosseini, Baicen Xiao, Andrew Clark +1

Due to the growth of video data on Internet, automatic video analysis has gained a lot of attention from academia as well as companies such as Facebook, Twitter and Google. In this…

cs.CV20172 cited

Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos

Hossein Hosseini, Baicen Xiao, Radha Poovendran

Despite the rapid progress of the techniques for image classification, video annotation has remained a challenging task. Automated video annotation would be a breakthrough technolo…