Statistically Robust Neural Network Classification

12/10/2019
by   Benjie Wang, et al.
0

Recently there has been much interest in quantifying the robustness of neural network classifiers through adversarial risk metrics. However, for problems where test-time corruptions occur in a probabilistic manner, rather than being generated by an explicit adversary, adversarial metrics typically do not provide an accurate or reliable indicator of robustness. To address this, we introduce a statistically robust risk (SRR) framework which measures robustness in expectation over both network inputs and a corruption distribution. Unlike many adversarial risk metrics, which typically require separate applications on a point-by-point basis, the SRR can easily be directly estimated for an entire network and used as a training objective in a stochastic gradient scheme. Furthermore, we show both theoretically and empirically that it can scale to higher-dimensional networks by providing superior generalization performance compared with comparable adversarial risks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/04/2018

Lipschitz Networks and Distributional Robustness

Robust risk minimisation has several advantages: it has been studied wit...
research
11/10/2022

Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses

Keyless entry systems in cars are adopting neural networks for localizin...
research
10/22/2018

Adversarial Risk Bounds for Binary Classification via Function Transformation

We derive new bounds for a notion of adversarial risk, characterizing th...
research
10/21/2021

RoMA: a Method for Neural Network Robustness Measurement and Assessment

Neural network models have become the leading solution for a large varie...
research
02/15/2018

Adversarial Risk and the Dangers of Evaluating Against Weak Attacks

This paper investigates recently proposed approaches for defending again...
research
11/29/2019

Adversarially Robust Low Dimensional Representations

Adversarial or test time robustness measures the susceptibility of a mac...

Please sign up or login with your details

Forgot password? Click here to reset