Goto

Collaborating Authors

 output space


Center Smoothing: Certified Robustness for Networks with Structured Outputs

Neural Information Processing Systems

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured outputs like sets, images, language, etc.









7990ec44fcf3d7a0e5a2add28362213c-Paper.pdf

Neural Information Processing Systems

We propose in this paper a general framework for deriving loss functions for structured prediction. Inourframework,theuserchooses aconvexsetincluding the output space and provides an oracle forprojectingonto that set.