Timezone: »

 
Poster
Center Smoothing: Certified Robustness for Networks with Structured Outputs
Aounon Kumar · Tom Goldstein

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

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. We model the output space as a metric space under a distance/similarity function, such as intersection-over-union, perceptual similarity, total variation distance, etc. Such models are used in many machine learning problems like image segmentation, object detection, generative models, image/audio-to-text systems, etc. Based on a robustness technique called randomized smoothing, our center smoothing procedure can produce models with the guarantee that the change in the output, as measured by the distance metric, remains small for any norm-bounded adversarial perturbation of the input. We apply our method to create certifiably robust models with disparate output spaces -- from sets to images -- and show that it yields meaningful certificates without significantly degrading the performance of the base model.

Keywords: Machine Learning · Robustness · Adversarial Robustness and Security · Vision · Generative Model

Author Information

Aounon Kumar (University of Maryland, College Park)
Tom Goldstein (Rice University)

More from the Same Authors