Center Smoothing for Certifiably Robust Vector-Valued Functions

by   Aounon Kumar, et al.

Randomized smoothing has been successfully applied in high-dimensional image classification tasks to obtain models that are provably robust against input perturbations of bounded size. We extend this technique to produce certifiable robustness for vector-valued functions, i.e., bound the change in output caused by a small change in input. These functions are used in many areas of machine learning, such as image reconstruction, dimensionality reduction, super-resolution, etc., but due to the enormous dimensionality of the output space in these problems, generating meaningful robustness guarantees is difficult. We design a smoothing procedure that can leverage the local, potentially low-dimensional, behaviour of the function around an input to obtain probabilistic robustness certificates. We demonstrate the effectiveness of our method on multiple learning tasks involving vector-valued functions with a wide range of input and output dimensionalities.



page 7


Intriguing Properties of Input-dependent Randomized Smoothing

Randomized smoothing is currently considered the state-of-the-art method...

Extensions and limitations of randomized smoothing for robustness guarantees

Randomized smoothing, a method to certify a classifier's decision on an ...

Post-Estimation Smoothing: A Simple Baseline for Learning with Side Information

Observational data are often accompanied by natural structural indices, ...

Super-Resolution Image Reconstruction Based on Self-Calibrated Convolutional GAN

With the effective application of deep learning in computer vision, brea...

SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions

State-of-the-art NLP models can often be fooled by human-unaware transfo...

All-Optical Information Processing Capacity of Diffractive Surfaces

Precise engineering of materials and surfaces has been at the heart of s...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.