skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Adversarial attacks on medical machine learning

Science (American Association for the Advancement of Science), 2019-03, Vol.363 (6433), p.1287-1289 [Peer Reviewed Journal]

Copyright © 2019, American Association for the Advancement of Science ;ISSN: 0036-8075 ;EISSN: 1095-9203 ;DOI: 10.1126/science.aaw4399 ;PMID: 30898923

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Adversarial attacks on medical machine learning
  • Author: Finlayson, Samuel G ; Bowers, John D ; Ito, Joichi ; Zittrain, Jonathan L ; Beam, Andrew L ; Kohane, Isaac S
  • Subjects: Artificial intelligence ; Fraud ; Health care ; Humans ; Innovations ; Insurance Claim Review ; Learning algorithms ; Machine Learning ; Medical innovations
  • Is Part Of: Science (American Association for the Advancement of Science), 2019-03, Vol.363 (6433), p.1287-1289
  • Description: Emerging vulnerabilities demand new conversations With public and academic attention increasingly focused on the new role of machine learning in the health information economy, an unusual and no-longer-esoteric category of vulnerabilities in machine-learning systems could prove important. These vulnerabilities allow a small, carefully designed change in how inputs are presented to a system to completely alter its output, causing it to confidently arrive at manifestly wrong conclusions. These advanced techniques to subvert otherwise-reliable machine-learning systems—so-called adversarial attacks—have, to date, been of interest primarily to computer science researchers ( 1 ). However, the landscape of often-competing interests within health care, and billions of dollars at stake in systems' outputs, implies considerable problems. We outline motivations that various players in the health care system may have to use adversarial attacks and begin a discussion of what to do about them. Far from discouraging continued innovation with medical machine learning, we call for active engagement of medical, technical, legal, and ethical experts in pursuit of efficient, broadly available, and effective health care that machine learning will enable.
  • Publisher: United States: The American Association for the Advancement of Science
  • Language: English
  • Identifier: ISSN: 0036-8075
    EISSN: 1095-9203
    DOI: 10.1126/science.aaw4399
    PMID: 30898923
  • Source: MEDLINE
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait