Towards Understanding the Space of Unrobust Features of Neural Networks

Liao Bingli, Takahiro Kanzaki, Danilo Vasconcellos Vargas

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Despite the convolutional neural network has achieved tremendous monumental success on a variety of computer vision-related tasks, it is still extremely challenging to build a neural network with doubtless reliability. Previous works have demonstrated that the deep neural network can be efficiently fooled by human imperceptible perturbation to the input, which actually revealed the instability for interpolation. Like human-beings, an ideally trained neural network should be constrained within desired inference space and maintain correctness for both interpolation and extrapolation. In this paper, we develop a technique to verify the correctness when convolutional neural networks extrapolate beyond training data distribution by generating legitimated feature broken images, and we show that the decision boundary for convolutional neural network is not well formulated based on image features for extrapolating.

Original languageEnglish
Title of host publication2021 5th IEEE International Conference on Cybernetics, CYBCONF 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages91-94
Number of pages4
ISBN (Electronic)9781665403207
DOIs
Publication statusPublished - Jun 8 2021
Event5th IEEE International Conference on Cybernetics, CYBCONF 2021 - Virtual, Sendai, Japan
Duration: Jun 8 2021Jun 10 2021

Publication series

Name2021 5th IEEE International Conference on Cybernetics, CYBCONF 2021

Conference

Conference5th IEEE International Conference on Cybernetics, CYBCONF 2021
Country/TerritoryJapan
CityVirtual, Sendai
Period6/8/216/10/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Towards Understanding the Space of Unrobust Features of Neural Networks'. Together they form a unique fingerprint.

Cite this