Showing 2022Show all
2 papers · 1 filter
cs.LG2022
A Theoretical Study of The Effects of Adversarial Attacks on Sparse Regression
Deepak Maurya, Jean Honorio
This paper analyzes regularized linear regression under the challenging scenario of having only adversarially corrupted data for training. We use the primal-dual witness p…
cs.LG2022
A Novel Plug-and-Play Approach for Adversarially Robust Generalization
Deepak Maurya, Adarsh Barik, Jean Honorio
In this work, we propose a robust framework that employs adversarially robust training to safeguard the ML models against perturbed testing data. Our contributions can be seen from…