Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 50048 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Jalili, Rasool
- Abstract:
- A traffic classifier maps each input stream into a pre-defined traffic class. If the traffic is encrypted using a protocol, such as SSL, or is protected using an encrypted tunnel, it's content would be hidden from the classifier, in which case the common traffic classification methods will be ineffective. Although common security mechanisms which provide information confidentiality to user can't hide all properties of messages, including length and time. Some of the newly presented methods of traffic classification utilize these properties and can actually classify messages without accessing their content. We will study such methods and their limitations in this thesis. Of all the encrypted traffic classifiers, we will focus on classifying websites for encrypted traffic. After checking current methods, a new method on classifying the encrypted traffic of websites will be presented. Also we want these properties to be less sensitive to assumptions considered about encrypted traffic in the research area of this field. We will evaluate the presented method using two collected data sets and compare the results to current website classifiers of encrypted traffics. Furthermore we will compare our presented method to the other currently existing ones from a view point of quality and the number of used properties
- Keywords:
- Encrypted Traffic ; Machine Learning ; Traffic Analysis ; Traffic Classification
Digital Object List
-
محتواي کتاب
- view
Bookmark