2 papers
cs.CV2019
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…