Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Search and detection of suspicious social media web pages

Search and detection of illegal web content
: Coote, R.; Rein, K.; Schade, U.

Lauster, Michael (Hrsg.) ; Fraunhofer Verbund Verteidigungs- und Sicherheitsforschung; Fraunhofer-Institut für Naturwissenschaftlich-Technische Trendanalysen -INT-, Euskirchen:
8th Future Security 2013. Security Research Conference : Berlin, September 17 - 19, 2013. Proceedings
Stuttgart: Fraunhofer Verlag, 2013
ISBN: 3-8396-0604-7
ISBN: 978-3-8396-0604-9
Security Research Conference "Future Security" <8, 2013, Berlin>
Conference Paper
Fraunhofer FKIE

The World-Wide Web has become a great resource for information and communication throughout the world. However, at the same time, it also has long been abused as a platform for criminals to collaborate on a whole range of criminal activity. In the last ten years law enforcement agencies have started to establish organizational units dedicated to the task of performing general scanning on the web. Due to the vast growth of information on the Web and the limited personnel and time resources, this is a quite challenging task. In this paper we describe current work on a web-mining system to support criminal investigators in performing general scanning for suspicious or illegal web pages. The system automatically analyses websites, learning to classify sites, enabling it to filter and automatically differentiate between suspicious and innocuous web content. The analyst is freed from having to examine individually every single URL from the list of websites which have been crawled. In order to learn class models for the algorithm, we apply a simple yet powerful learning method known as the perceptron algorithm.