Anzeige
Erschienen in:
2018 | OriginalPaper | Buchkapitel
Smart Device Fingerprinting Based on Webpage Loading
verfasst von : Peng Fang, Liusheng Huang, Hongli Xu, Qijian He
Erschienen in: Wireless Algorithms, Systems, and Applications
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Detecting devices connected to a network has become of serious importance for the network. Different devices differ in CPU scheduler, screen resolution and clock frequency, resulting in different performances when loading the same webpage. In this paper, we present a content-agnostic device identification method, a technique which decomposes webpage loading time and loads as the features to identify physical devices. This proposed method can deal with various types of devices such as mobiles, laptops, and other smart devices. We conduct experiments to evaluate the performance of the proposed method with real-world traffic. The experiment results demonstrate that the proposed method can accurately identify the types of devices from encrypted traffic and the recognition rate can reach \(98.4\%\). To demonstrate the scalability of the method, we heuristically applied it to website identification and found that it has better effects than existing methods.