43 citations · 54 across the 3 of their papers we have counts for
3 papers
cs.CV2019★ 43 cited
Defending Against Universal Attacks Through Selective Feature Regeneration
Tejas Borkar, Felix Heide, Lina Karam
Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, image-agnostic (universal adversarial) perturba…
cs.CV2018
Generative Sensing: Transforming Unreliable Sensor Data for Reliable Recognition
Lina Karam, Tejas Borkar, Yu Cao +1
This paper introduces a deep learning enabled generative sensing framework which integrates low-end sensors with computational intelligence to attain a high recognition accuracy on…
cs.CV2017★ 11 cited
DeepCorrect: Correcting DNN models against Image Distortions
Tejas Borkar, Lina Karam
In recent years, the widespread use of deep neural networks (DNNs) has facilitated great improvements in performance for computer vision tasks like image classification and object…