Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Analyzing the noise robustness of deep neural networks

Cao, Kelei, Liu, Mengchen, Su, Hang, Wu, Jing, Zhu, Jun and Liu, Shixia 2020. Analyzing the noise robustness of deep neural networks. IEEE Transactions on Visualization and Computer Graphics , p. 1. 10.1109/TVCG.2020.2969185

[img]
Preview
PDF - Accepted Post-Print Version
Download (10MB) | Preview

Abstract

Adversarial examples, generated by adding small but intentionally imperceptible perturbations to normal examples, can mislead deep neural networks (DNNs) to make incorrect predictions. Although much work has been done on both adversarial attack and defense, a fine-grained understanding of adversarial examples is still lacking. To address this issue, we present a visual analysis method to explain why adversarial examples are misclassified. The key is to compare and analyze the datapaths of both the adversarial and normal examples. A datapath is a group of critical neurons along with their connections. We formulate the datapath extraction as a subset selection problem and solve it by constructing and training a neural network. A multi-level visualization consisting of a network-level visualization of data flows, a layer-level visualization of feature maps, and a neuron-level visualization of learned features, has been designed to help investigate how datapaths of adversarial and normal examples diverge and merge in the prediction process. A quantitative evaluation and a case study were conducted to demonstrate the promise of our method to explain the misclassification of adversarial examples.

Item Type: Article
Date Type: Published Online
Status: In Press
Schools: Computer Science & Informatics
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
ISSN: 1077-2626
Date of First Compliant Deposit: 4 February 2020
Date of Acceptance: 20 January 2020
Last Modified: 10 Mar 2020 23:01
URI: http://orca.cf.ac.uk/id/eprint/129315

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics