RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing
Randomized smoothing has shown promising certified robustness against adversaries in classification tasks. Despite such success with only zeroth-order access to base models, randomized smoothing has not been extended to a general form of regression. By defining robustness in regression tasks flexibly through probabilities, we demonstrate how to establish upper bounds on input data point perturbation (using the $\ell_2$ norm) for a user-specified probability of observing valid outputs. Furthermore, we showcase the asymptotic property of a basic averaging function in scenarios where the regression model operates without any constraint. We then derive a certified upper bound of the input perturbations when dealing with a family of regression models where the outputs are bounded. Our simulations verify the validity of the theoretical results and reveal the advantages and limitations of simple smoothing functions, i.e., averaging, in regression tasks. The code is publicly available at \url{https://github.com/arekavandi/Certified_Robust_Regression}.
Code (1)
Tasks
regressionvalidMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Detection as Regression: Certified Object Detection with Median Smoothing
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image classifiers, a direct extension to objec…
Objectobject-detectionObject DetectionregressionDetection as Regression: Certified Object Detection by Median Smoothing
Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image classifiers, a direct extension to objec…
Objectobject-detectionObject DetectionregressionHigher-Order Certified Robustness for Regression
Randomized smoothing has emerged as a scalable technique for certifying the adversarial robustness of classifiers. However, its application to regression remains under-explored and faces unique challenges. Existing regre…
Adversarial RobustnessCertified Adversarial Robustness via Randomized Smoothing
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique ha…
Adversarial DefenseAdversarial RobustnessRobust classificationBridging the Theoretical Gap in Randomized Smoothing
Randomized smoothing has become a leading approach for certifying adversarial robustness in machine learning models. However, a persistent gap remains between theoretical certified robustness and empirical robustness acc…
Adversarial Robustness