A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples

by   Beilun Wang, et al.

Most machine learning classifiers, including deep neural networks, are vulnerable to adversarial examples. Such inputs are typically generated by adding small but purposeful modifications that lead to incorrect outputs while imperceptible to human eyes. The goal of this paper is not to introduce a single method, but to make theoretical steps towards fully understanding adversarial examples. By using concepts from topology, our theoretical analysis brings forth the key reasons why an adversarial example can fool a classifier (f_1) and adds its oracle (f_2, like human eyes) in such analysis. By investigating the topological relationship between two (pseudo)metric spaces corresponding to predictor f_1 and oracle f_2, we develop necessary and sufficient conditions that can determine if f_1 is always robust (strong-robust) against adversarial examples according to f_2. Interestingly our theorems indicate that just one unnecessary feature can make f_1 not strong-robust, and the right feature representation learning is the key to getting a classifier that is both accurate and strong-robust.



There are no comments yet.


page 35


Understanding and Quantifying Adversarial Examples Existence in Linear Classification

State-of-art deep neural networks (DNN) are vulnerable to attacks by adv...

Proper measure for adversarial robustness

This paper analyzes the problems of standard adversarial accuracy and st...

Playing it Safe: Adversarial Robustness with an Abstain Option

We explore adversarial robustness in the setting in which it is acceptab...

Adversarial Examples Make Strong Poisons

The adversarial machine learning literature is largely partitioned into ...

Adversarial Examples Are Not Bugs, They Are Features

Adversarial examples have attracted significant attention in machine lea...

Consistent Non-Parametric Methods for Adaptive Robustness

Learning classifiers that are robust to adversarial examples has receive...

Adversarial Examples from Cryptographic Pseudo-Random Generators

In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we arg...
This week in AI

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