Certified Robustness

Provably Robust Cost-Sensitive Learning via Randomized Smoothing
Study how to certify and train for cost-sensitive robustness using randomized smoothing.
Yuan Xin, Michael Backes, Xiao Zhang
PDF Cite Code ArXiv
Cost-Sensitive Robustness against Adversarial Examples
We propose a notion of cost-sensitive robustness for measuring classifier’s performance when adversarial transformations are not equally important, and provide a certified robust training method to optimize for it.
Xiao Zhang, David Evans
PDF Cite Code Poster ArXiv OpenReview Post
Cost-Sensitive Robustness against Adversarial Examples