Abstract
Website fingerprinting (WFP) could infer which websites a user is accessing via an encrypted proxy by passively inspecting the traffic between the user and the proxy. The key to WFP is designing a classifier capable of distinguishing traffic characteristics of accessing different websites. However, when deployed in real-life networks, a well-trained classifier may face a significant obstacle of training-testing asymmetry, which fundamentally limits its practicability. Specifically, although pure traffic samples can be collected in a controlled (clean) testbed for training, the classifier may fail to extract such pure traffic samples as its input from raw complicated traffic for testing. In this paper, we are interested in encrypted proxies that relay connections between the user and the proxy individually (e.g., Shadowsocks), and design a context-aware system using built-in spatial-temporal flow correlation to address the obstacle. Extensive experiments demonstrate that our system does not only enable WFP against a popular type of encrypted proxies practical, but also achieves better performance than ideally training/testing pure samples.
Original language | American English |
---|---|
Title of host publication | IEEE INFOCOM 2021 - IEEE Conference on Computer Communications |
Publisher | IEEE |
ISBN (Electronic) | 978-1-6654-0325-2 |
ISBN (Print) | 978-1-6654-3131-6 |
DOIs | |
State | Published - Jul 26 2021 |
Event | 40th IEEE Conference on Computer Communications, INFOCOM 2021 - Vancouver, Canada Duration: May 10 2021 → May 13 2021 |
Conference
Conference | 40th IEEE Conference on Computer Communications, INFOCOM 2021 |
---|---|
Country/Territory | Canada |
City | Vancouver |
Period | 5/10/21 → 5/13/21 |
ASJC Scopus Subject Areas
- General Computer Science
- Electrical and Electronic Engineering
Keywords
- Training
- Correlation
- Conferences
- Fingerprint recognition
- Relays
- Faces
Disciplines
- Computer Sciences
- Engineering