DeepAI AI Chat
Log In Sign Up

Measuring the Robustness of Graph Properties

12/03/2018
by   Yali Wan, et al.
Amazon
0

In this paper, we propose a perturbation framework to measure the robustness of graph properties. Although there are already perturbation methods proposed to tackle this problem, they are limited by the fact that the strength of the perturbation cannot be well controlled. We firstly provide a perturbation framework on graphs by introducing weights on the nodes, of which the magnitude of perturbation can be easily controlled through the variance of the weights. Meanwhile, the topology of the graphs are also preserved to avoid uncontrollable strength in the perturbation. We then extend the measure of robustness in the robust statistics literature to the graph properties.

READ FULL TEXT
10/04/2022

Strength-Adaptive Adversarial Training

Adversarial training (AT) is proved to reliably improve network's robust...
05/03/2019

Transfer of Adversarial Robustness Between Perturbation Types

We study the transfer of adversarial robustness of deep neural networks ...
07/16/2020

Learning perturbation sets for robust machine learning

Although much progress has been made towards robust deep learning, a sig...
03/24/2023

On the connection between the ABS perturbation methodology and differential privacy

This paper explores analytical connections between the perturbation meth...
05/06/2021

Understanding Catastrophic Overfitting in Adversarial Training

Recently, FGSM adversarial training is found to be able to train a robus...
01/29/2021

Topological Interference Management with Adversarial Perturbation

In this paper, we consider the topological interference management (TIM)...
02/15/2022

Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis

A variety of methods have been proposed to try to explain how deep neura...