134 citations · 258 across the 6 of their papers we have counts for
11 papers
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…
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…
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…
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…
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…
Google's Cloud Vision API Is Not Robust To Noise
Hossein Hosseini, Baicen Xiao, Radha Poovendran
Google has recently introduced the Cloud Vision API for image analysis. According to the demonstration website, the API "quickly classifies images into thousands of categories, det…
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…
Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
Hossein Hosseini, Yize Chen, Sreeram Kannan +2
Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broa…
On the Limitation of Convolutional Neural Networks in Recognizing Negative Images
Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal +1
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance on a variety of computer vision tasks, particularly visual classification problems, where new algori…
Deceiving Google's Perspective API Built for Detecting Toxic Comments
Hossein Hosseini, Sreeram Kannan, Baosen Zhang +1
Social media platforms provide an environment where people can freely engage in discussions. Unfortunately, they also enable several problems, such as online harassment. Recently,…
Learning Temporal Dependence from Time-Series Data with Latent Variables
Hossein Hosseini, Sreeram Kannan, Baosen Zhang +1
We consider the setting where a collection of time series, modeled as random processes, evolve in a causal manner, and one is interested in learning the graph governing the relatio…