Showing cs.CVShow all
2 papers · 1 filter
cs.CV2019
Reconstructing Network Inputs with Additive Perturbation Signatures
Nick Moran, Chiraag Juvekar
In this work, we present preliminary results demonstrating the ability to recover a significant amount of information about secret model inputs given only very limited access to mo…
cs.CV2018
Protecting JPEG Images Against Adversarial Attacks
Aaditya Prakash, Nick Moran, Solomon Garber +2
As deep neural networks (DNNs) have been integrated into critical systems, several methods to attack these systems have been developed. These adversarial attacks make imperceptible…