82 citations · 133 across the 12 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.CV2019
Improved Adversarial Robustness by Reducing Open Space Risk via Tent Activations
Andras Rozsa, Terrance E. Boult
Adversarial examples contain small perturbations that can remain imperceptible to human observers but alter the behavior of even the best performing deep learning models and yield…
cs.CV2019★ 12 cited
SpliceRadar: A Learned Method For Blind Image Forensics
Aurobrata Ghosh, Zheng Zhong, Terrance E Boult +1
Detection and localization of image manipulations like splices are gaining in importance with the easy accessibility of image editing softwares. While detection generates a verdict…