By Topic

Subverting prediction in adversarial settings

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
J. G. Dutrisac ; School of Computing, Queen¿s University Kingston Canada ; D. B. Skillicorn

We show that two mainstream prediction techniques, support vector machines and decision trees, are easily subverted by inserting carefully-chosen training records. Furthermore, the relationship between the properties of the inserted record(s) and the regions for which the predictor will subsequently misclassify can be inferred, so desired misclassifications can be forced. In adversarial settings, it is plausible that manipulation of this kind will be attempted, so this has implications for the design of prediction systems and the use of off-the-shelf technology, especially as support vector machines are one of the most powerful prediction algorithms known.

Published in:

Intelligence and Security Informatics, 2008. ISI 2008. IEEE International Conference on

Date of Conference:

17-20 June 2008