377 citations · 582 across the 13 of their papers we have counts for
4 papers · 1 filter
NAG: Network for Adversary Generation
Konda Reddy Mopuri, Utkarsh Ojha, Utsav Garg +1
Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifi…
CNN Fixations: An unraveling approach to visualize the discriminative image regions
Konda Reddy Mopuri, Utsav Garg, R. Venkatesh Babu
Deep convolutional neural networks (CNN) have revolutionized various fields of vision research and have seen unprecedented adoption for multiple tasks such as classification, detec…
Fast Feature Fool: A data independent approach to universal adversarial perturbations
Konda Reddy Mopuri, Utsav Garg, R. Venkatesh Babu
State-of-the-art object recognition Convolutional Neural Networks (CNNs) are shown to be fooled by image agnostic perturbations, called universal adversarial perturbations. It is a…
Deep image representations using caption generators
Konda Reddy Mopuri, Vishal B. Athreya, R. Venkatesh Babu
Deep learning exploits large volumes of labeled data to learn powerful models. When the target dataset is small, it is a common practice to perform transfer learning using pre-trai…