Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A framework for quantitative security analysis of machine learning

 
: Laskov, P.; Kloft, M.

:

Association for Computing Machinery -ACM-:
AISec 2009, 2nd ACM Workshop on Security and Artificial Intelligence. Proceedings : Chicago, Illinois, USA, November 09 - 09, 2009
New York: ACM, 2009
ISBN: 978-1-60558-781-3
pp.1-4
Workshop on Security and Artificial Intelligence (AISec) <2, 2009, Chicago/Ill.>
Computer and Communications Security Conference (CCS) <16, 2009, Chicago/Ill.>
English
Conference Paper
Fraunhofer FIRST ()

Abstract
We propose a framework for quantitative security analysis of machine learning methods. The key parts of this framework are the formal specification of a deployed learning model and attacker's constraints, the computation of an optimal attack, and the derivation of an upper bound on adversarial impact. We exemplarily apply the framework for the analysis of one specific learning scenario, online centroid anomaly detection, and experimentally verify the tightness of obtained theoretical bounds.

: http://publica.fraunhofer.de/documents/N-188231.html