Towards an anomaly detection technique for web services based on kernel methods

  • Authors:
  • Reyhaneh Ghasem Esfahani;Mohammad Abdollahi Azgomi

  • Affiliations:
  • School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran;School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran

  • Venue:
  • IIT'09 Proceedings of the 6th international conference on Innovations in information technology
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

A large number of enterprises are turning to service-oriented architecture (SOA) for designing, using and managing their information technology (IT) systems. SOAP-based web services are the most commonly found services in today's SOA implementations. This paper reviews different possible classes of vulnerabilities in web services and investigates the advantages and shortcomings of available solutions. We aim to find an anomaly detection method, which is sensitive to XML semistructured data and is appropriate for web services. For this purpose, a new approach for anomaly detection in web services is proposed by employing kernel methods. The proposed technique is capable of detecting new unknown attacks in XML contents of the SOAP messages.