English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Adversarial vulnerabilities of human decision-making

Dezfouli, A., Nock, R., & Dayan, P. (2020). Adversarial vulnerabilities of human decision-making. Proceedings of the National Academy of Sciences of the United States of America, 117(46): 202016921, pp. 29221-29228. doi:10.1073/pnas.2016921117.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0007-5AD3-6 Version Permalink: https://hdl.handle.net/21.11116/0000-0007-6E0A-4
Genre: Journal Article

Files

show Files

Locators

show
hide
Locator:
https://www.pnas.org/content/pnas/117/46/29221.full.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Dezfouli, A, Author
Nock, R, Author
Dayan, P1, 2, Author           
Affiliations:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Adversarial examples are carefully crafted input patterns that are surprisingly poorly classified by artificial and/or natural neural networks. Here we examine adversarial vulnerabilities in the processes responsible for learning and choice in humans. Building upon recent recurrent neural network models of choice processes, we propose a general framework for generating adversarial opponents that can shape the choices of individuals in particular decision-making tasks toward the behavioral patterns desired by the adversary. We show the efficacy of the framework through three experiments involving action selection, response inhibition, and social decision-making. We further investigate the strategy used by the adversary in order to gain insights into the vulnerabilities of human choice. The framework may find applications across behavioral sciences in helping detect and avoid flawed choice.

Details

show
hide
Language(s):
 Dates: 2020-11
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1073/pnas.2016921117
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the National Academy of Sciences of the United States of America
  Other : Proc. Acad. Sci. USA
  Other : Proc. Acad. Sci. U.S.A.
  Other : Proceedings of the National Academy of Sciences of the USA
  Abbreviation : PNAS
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Washington, D.C. : National Academy of Sciences
Pages: - Volume / Issue: 117 (46) Sequence Number: 202016921 Start / End Page: 29221 - 29228 Identifier: ISSN: 0027-8424
CoNE: https://pure.mpg.de/cone/journals/resource/954925427230