TCP - IP White Papers
A Robust Classifier for Passive TCP/IP Fingerprinting
Overview Using probabilistic learning, a naive Bayesian classifier to passively infer a host's operating system from packet headers is developed. The authors analyze traffic captured from an Internet exchange point and compare this classifier to rule-based inference tools. While the host operating system distribution is heavily skewed, the authors found operating systems that constitute a small fraction of the host count contribute a majority of total traffic. Finally as an application of this classifier, the number of hosts masquerading behind NAT devices is counted and results against prior techniques are evaluate.
| Publisher | Massachusetts Institute of Technology | File Format | |
|---|---|---|---|
| Date Published | February 2004 | ||
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful? 1 out of 1 users found this white paper useful
White Paper RSS
Download
Register
