Remote OS fingerprinting is valuable in areas such as network security, Internet modeling, and end-to-end application design, etc. While current rule-based tools fail to detect the OS of remote host with high accuracy, for users may modify their TCP/IP parameters or employ stack "scrubbers". In this paper, a BP neural network based classifier is proposed for accurately finger-printing the OS of remote host. To avoid the shortages of traditional BP algorithm, the classifier is also enforced with Levenberg-Marquardt algorithm. Experimental results on packet traces collected at an access link of a website show that, rule-based tools can't identify as many as 10.6% of the hosts. While the BP neural network based classifier is far more accurate, it can successfully identify about 97.8% hosts in the experiment. © Springer-Verlag Berlin Heidelberg 2005.
CITATION STYLE
Li, W., Zhang, D., & Yang, J. (2005). Remote OS fingerprinting using BP neural network. In Lecture Notes in Computer Science (Vol. 3498, pp. 367–372). Springer Verlag. https://doi.org/10.1007/11427469_59
Mendeley helps you to discover research relevant for your work.