A New Website Fingerprinting Method for Tor Hidden Service

Although anonymous communication systems protect user privacy, they also facilitate evasion of network censorship. Currently, evaders use anonymous hidden services to carry out various illegal activities, which pose a serious threat to network management. To address this problem, a new website finge...

Full description

Saved in:
Bibliographic Details
Main Authors: Zihang Hui, Jiangtao Zhai, Shengxian Wang, Weijie Ji
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10818427/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832592847775203328
author Zihang Hui
Jiangtao Zhai
Shengxian Wang
Weijie Ji
author_facet Zihang Hui
Jiangtao Zhai
Shengxian Wang
Weijie Ji
author_sort Zihang Hui
collection DOAJ
description Although anonymous communication systems protect user privacy, they also facilitate evasion of network censorship. Currently, evaders use anonymous hidden services to carry out various illegal activities, which pose a serious threat to network management. To address this problem, a new website fingerprinting method that combines the Bidirectional Encoder Representations from Transformers (BERT) model and a Long Short-Term Memory (LSTM) network was proposed to improve the accuracy of website fingerprinting for Tor hidden services. The proposed method uses the BERT model to extract the semantic features of webpage content, and the LSTM model is combined to capture the long-term dependencies to achieve efficient recognition of website fingerprints. This method not only deals with the homepage, but also considers the features of sub-pages in depth, which can effectively improve the performance of the model in closed-world and open-world scenarios through deep textual and time-series feature learning. The experimental results show that compared with existing state-of-the-art techniques, the proposed method exhibits better performance in terms of key performance metrics.
format Article
id doaj-art-365a6f2a14ee4e79a31f7a72c54634a4
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-365a6f2a14ee4e79a31f7a72c54634a42025-01-21T00:02:19ZengIEEEIEEE Access2169-35362025-01-01138886889710.1109/ACCESS.2024.352392510818427A New Website Fingerprinting Method for Tor Hidden ServiceZihang Hui0https://orcid.org/0009-0009-1044-0919Jiangtao Zhai1https://orcid.org/0000-0001-8557-9899Shengxian Wang2Weijie Ji3Department of Computer and Software, Nanjing University of Information Science and Technology, Nanjing, ChinaDepartment of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, ChinaDepartment of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, ChinaDepartment of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing, ChinaAlthough anonymous communication systems protect user privacy, they also facilitate evasion of network censorship. Currently, evaders use anonymous hidden services to carry out various illegal activities, which pose a serious threat to network management. To address this problem, a new website fingerprinting method that combines the Bidirectional Encoder Representations from Transformers (BERT) model and a Long Short-Term Memory (LSTM) network was proposed to improve the accuracy of website fingerprinting for Tor hidden services. The proposed method uses the BERT model to extract the semantic features of webpage content, and the LSTM model is combined to capture the long-term dependencies to achieve efficient recognition of website fingerprints. This method not only deals with the homepage, but also considers the features of sub-pages in depth, which can effectively improve the performance of the model in closed-world and open-world scenarios through deep textual and time-series feature learning. The experimental results show that compared with existing state-of-the-art techniques, the proposed method exhibits better performance in terms of key performance metrics.https://ieeexplore.ieee.org/document/10818427/BERT modelencrypted traffic detectionhidden servicesLSTM networkwebsite fingerprinting
spellingShingle Zihang Hui
Jiangtao Zhai
Shengxian Wang
Weijie Ji
A New Website Fingerprinting Method for Tor Hidden Service
IEEE Access
BERT model
encrypted traffic detection
hidden services
LSTM network
website fingerprinting
title A New Website Fingerprinting Method for Tor Hidden Service
title_full A New Website Fingerprinting Method for Tor Hidden Service
title_fullStr A New Website Fingerprinting Method for Tor Hidden Service
title_full_unstemmed A New Website Fingerprinting Method for Tor Hidden Service
title_short A New Website Fingerprinting Method for Tor Hidden Service
title_sort new website fingerprinting method for tor hidden service
topic BERT model
encrypted traffic detection
hidden services
LSTM network
website fingerprinting
url https://ieeexplore.ieee.org/document/10818427/
work_keys_str_mv AT zihanghui anewwebsitefingerprintingmethodfortorhiddenservice
AT jiangtaozhai anewwebsitefingerprintingmethodfortorhiddenservice
AT shengxianwang anewwebsitefingerprintingmethodfortorhiddenservice
AT weijieji anewwebsitefingerprintingmethodfortorhiddenservice
AT zihanghui newwebsitefingerprintingmethodfortorhiddenservice
AT jiangtaozhai newwebsitefingerprintingmethodfortorhiddenservice
AT shengxianwang newwebsitefingerprintingmethodfortorhiddenservice
AT weijieji newwebsitefingerprintingmethodfortorhiddenservice