A New Poisoning Attacks on Deep Neural Networks

Jung Shian Li, Yen Chu Peng, I-Hsien Liu, Chuan Gang Liu

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

1 Citation (Scopus)

Abstract

In healthcare field, many machine learning schemes have been applied in analyzing image content dataset. Among them, deep neural networks (DNNs), also known as deep learning, catches much attention. However, if deep neural networks are compromised by the attacker, medical diagnosis may be wrong, which leads to vital result. Recently, we find a new poisoning attack on DNNs may possibly happens due to poisoning dataset. This new poisoning attack, Category Diverse attack, has better ability to paralyze DNNs. Our performance experiments show our Category diverse attack actually leads to large accuracy drop of DNNs. We hope this discovery can help the information experts can improve the medical dataset quality in the future.

Original languageEnglish
Title of host publicationICMHI 2022 - 2022 6th International Conference on Medical and Health Informatics
PublisherAssociation for Computing Machinery
Pages24-27
Number of pages4
ISBN (Electronic)9781450396301
DOIs
Publication statusPublished - 2022 May 15
Event6th International Conference on Medical and Health Informatics, ICMHI 2022 - Virtual, Online, Japan
Duration: 2022 May 122022 May 15

Publication series

NameACM International Conference Proceeding Series

Conference

Conference6th International Conference on Medical and Health Informatics, ICMHI 2022
Country/TerritoryJapan
CityVirtual, Online
Period22-05-1222-05-15

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'A New Poisoning Attacks on Deep Neural Networks'. Together they form a unique fingerprint.

Cite this