Learning Securely.

The article discusses machine learning and an emerging field focused on exploring vulnerabilities in machine learning algorithms and ways to handle adversarial input by hackers. Topics include the impact of deep neural networks on potential applications and attacks of machine learning, the ability o...

Full description

Bibliographic Details
Published in:Communications of the ACM Vol. 59; no. 11; pp. 12 - 15
Main Author: Klarreich, Erica
Format: Article
Published: Association for Computing Machinery Nov2016
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=119379428&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 119379428
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00010782
        ACM
      jtl: Communications of the ACM
      issn: 00010782
      maglogo: N
    pubinfo:
      dt: Nov2016
      vid: 59
      iid: 11
      pid: 68
      pub: Association for Computing Machinery
    artinfo:
      ui:
        119379428
        10.1145/2994577
      ppf: 12
      ppct: 3
      formats:
      tig:
        atl: Learning Securely.
      aug:
        au: Klarreich, Erica
        affil: Mathematics and science journalist based in Berkeley, CA
      su:
        Machine learning
        Prevention of computer hacking
        Artificial neural networks
        Computer security
        Deep learning
      sug:
        subj:
          Machine learning
          Prevention of computer hacking
          Artificial neural networks
          Computer security
          Deep learning
      ab: The article discusses machine learning and an emerging field focused on exploring vulnerabilities in machine learning algorithms and ways to handle adversarial input by hackers. Topics include the impact of deep neural networks on potential applications and attacks of machine learning, the ability of hackers to transfer adversarial examples from one machine learning model to another, and the need for benchmarks and the integration of security during the development of machine learning algorithms.
      pubtype: Periodical
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2016
    holdings:
      @attributes:
        islocal: N