When Machine Learning meets Security Issues: A survey

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Machine learning is one of the most prevalent techniques in recent decades which has been widely applied in various fields. Among them, the applications that detect and defend potential adversarial attacks using machine learning method provide promising solutions in cybersecurity. At the same time, machine learning algorithms and systems are vulnerable to multiple security threats. In this paper, we revisit certain literatures and present a comprehensive survey from two respects, application of machine learning on cybersecurity and reliability and security of machine learning system. We then overview security issues of mobile AI devices and propose two notable focus, which are worthy in-depth studies in future. Researchers can regard this survey as a navigating reference in both machine learning and cybersecurity fields.

Original languageEnglish
Title of host publication2018 International Conference on Intelligence and Safety for Robotics, ISR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages158-165
Number of pages8
ISBN (Electronic)9781538655467
DOIs
StatePublished - 14 Nov 2018
Event2018 International Conference on Intelligence and Safety for Robotics, ISR 2018 - Shenyang, China
Duration: 24 Aug 201827 Aug 2018

Publication series

Name2018 International Conference on Intelligence and Safety for Robotics, ISR 2018

Conference

Conference2018 International Conference on Intelligence and Safety for Robotics, ISR 2018
Country/TerritoryChina
CityShenyang
Period24/08/1827/08/18

Keywords

  • Cybersecurity
  • Defense
  • Machine learning
  • Threats

Fingerprint

Dive into the research topics of 'When Machine Learning meets Security Issues: A survey'. Together they form a unique fingerprint.

Cite this