期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
卷号：4
期号：3
页码：1462
DOI：10.15680/IJIRSET.2015.0403092
出版社：S&S Publications
摘要：Pattern classification is a branch of machine learning that focuses on recognition of patterns andregularities in data. In adversarial applications like biometric authentication, spam filtering, network intrusion detectionthe pattern classification systems are used. As this adversarial scenario is not taken into account by classical designmethods, pattern classification systems may exhibit vulnerabilities, whose exploitation may severely affect theirperformance, and consequently limit their practical utility. Extending pattern classification theory and design methodsto adversarial settings is thus a novel and very relevant research direction, which has not yet been pursued in asystematic way. We propose a framework for evaluation of pattern security,model of adversary for defining any attackscenario. Reported results show that security evaluation can provide a more complete understanding of the classifier’sbehavior in adversarial environments, and lead to better design choices
