Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR

Abstract: 

Many state-of-the-art machine learning models such as deep neural networks have recently shown to be vulnerable to adversarial perturbations, especially in classification tasks. Motivated by adversarial machine learning, in this paper we investigate the robustness of sparse regression models with strongly correlated covariates to adversarially designed measurement noises. Specifically, we consider the family of ordered weighted L1 (OWL) regularized regression methods and study the case of OSCAR (octagonal shrinkage clustering algorithm for regression) in the adversarial setting. Under a norm-bounded threat model, we formulate the process of finding a maximally disruptive noise for OWL-regularized regression as an optimization problem and illustrate the steps towards finding such a noise in the case of OSCAR. Experimental results demonstrate that the regression performance of grouping strongly correlated features can be severely degraded under our adversarial setting, even when the noise budget is significantly smaller than the ground-truth signals.

up
0 users have voted:

Paper Details

Authors:
Pin-Yu Chen, Bhanukiran Vinzamuri and Sijia Liu
Submitted On:
23 November 2018 - 1:03pm
Short Link:
Type:
Poster
Event:
Document Year:
2018
Cite

Document Files

globalsip(3).pdf

(16)

Subscribe

[1] Pin-Yu Chen, Bhanukiran Vinzamuri and Sijia Liu, "Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3749. Accessed: Jul. 21, 2019.
@article{3749-18,
url = {http://sigport.org/3749},
author = {Pin-Yu Chen; Bhanukiran Vinzamuri and Sijia Liu },
publisher = {IEEE SigPort},
title = {Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR},
year = {2018} }
TY - EJOUR
T1 - Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR
AU - Pin-Yu Chen; Bhanukiran Vinzamuri and Sijia Liu
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3749
ER -
Pin-Yu Chen, Bhanukiran Vinzamuri and Sijia Liu. (2018). Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR. IEEE SigPort. http://sigport.org/3749
Pin-Yu Chen, Bhanukiran Vinzamuri and Sijia Liu, 2018. Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR. Available at: http://sigport.org/3749.
Pin-Yu Chen, Bhanukiran Vinzamuri and Sijia Liu. (2018). "Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR." Web.
1. Pin-Yu Chen, Bhanukiran Vinzamuri and Sijia Liu. Is Ordered Weighed L1 Regularized Regression Robust to Adversarial Perturbation ? A Case Study on OSCAR [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3749