3 papers
cs.LG2026
Behavioral Audit of Machine Unlearning Has a Privacy Cost
Liou Tang, James Joshi, Ashish Kundu
The removal of learned data from Machine Learning models through Machine Unlearning (MU) has been widely studied; however, there has yet to be an agreed-upon scheme for auditing MU…
cs.LG2025
Towards Strong Certified Defense with Universal Asymmetric Randomization
Hanbin Hong, Ashish Kundu, Ali Payani +2
Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distribu…
cs.CR2025
PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
Qin Yang, Nicholas Stout, Meisam Mohammady +6
Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient…