AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Tsinghua Science and Technology Article
PDF (10.3 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

From Traces to Packets: Realistic Deep Learning Based Multi-Tab Website Fingerprinting Attacks

College of Computer Science and Technology, Ocean University of China, Qingdao 266100, China
Department of Computer and Information Sciences, Temple University, Philadelphia, PA 19122, USA
Show Author Information

Abstract

Recent advancements in deep learning (DL) have introduced new security challenges in the form of side-channel attacks. A prime example is the website fingerprinting attack (WFA), which targets anonymity networks like Tor, enabling attackers to unveil users’ protected browsing activities from traffic data. While state-of-the-art WFAs have achieved remarkable results, they often rely on unrealistic single-website assumptions. In this paper, we undertake an exhaustive exploration of multi-tab website fingerprinting attacks (MTWFAs) in more realistic scenarios. We delve into MTWFAs and introduce MTWFA-SEG, a task involving the fine-grained packet-level classification within multi-tab Tor traffic. By employing deep learning models, we reveal their potential to threaten user privacy by discerning visited websites and browsing session timing. We design an improved fully convolutional model for MTWFA-SEG, which are enhanced by both network architecture advances and traffic data instincts. In the evaluations on interlocking browsing datasets, the proposed models achieve remarkable accuracy rates of over 68.6%, 71.8%, and 76.1% in closed, imbalanced open, and balanced open-world settings, respectively. Furthermore, the proposed models exhibit substantial robustness across diverse train-test settings. We further validate our designs in a coarse-grained task, MTWFA-MultiLabel, where they not only achieve state-of-the-art performance but also demonstrate high robustness in challenging situations.

Keywords

website fingerprintingmulti-tab website fingerprintinganonymity networkdeep learningside-channel attack

References

[1]

F. Buccafurri, V. De Angelis, M. F. Idone, C. Labrini, and S. Lazzaro, Achieving sender anonymity in tor against the global passive adversary, Appl. Sci., vol. 12, no. 1, p. 137, 2021.
Crossref Google Scholar
[2]
F. Buccafurri, V. De Angelis, M. F. Idone, and C. Labrini, Extending routes in tor to achieve recipient anonymity against the global adversary, in Proc. Int. Conf. Cyberworlds (CW ).Caen, France, 2021, pp. 238–245.
Crossref
[3]

J. Huang, Q. Huang, and W. Susilo, Leakage-resilient Group signature: Definitions and constructions, Inf. Sci., vol. 509, pp. 119–132, 2020.
Crossref Google Scholar
[4]
R. Dingledine, N. Mathewson, and P. Syverson, Tor: The second-generation onion router, in Proc. 13th Conf. USENIX Security Symposium, San Diego, CA, USA, 2004, p. 21.
Crossref
[5]

H. Yin, Y. Liu, Y. Li, Z. Guo, and Y. Wang, Defeating deep learning based de-anonymization attacks with adversarial example, J. Netw. Comput. Appl., vol. 220, p. 103733, 2023.
Crossref Google Scholar
[6]
P. Sirinam, M. Imani, M. Juarez, and M. Wright, Deep Fingerprinting: Undermining website fingerprinting defenses with deep learning, in Proc. 2018 ACM SIGSAC Conf. Computer and Communications Security, Toronto, Canada, 2018, pp. 1928–1943.
Crossref
[7]

S. Bhat, D. Lu, A. Kwon, and S. Devadas, Var-CNN: A data-efficient website fingerprinting attack based on deep learning, Proc. Priv. Enhancing Technol., vol. 2019, no. 4, pp. 292–310, 2019.
Crossref Google Scholar
[8]

M. Chen, Y. Wang, H. Xu, and X. Zhu, Few-shot website fingerprinting attack, Comput. Netw., vol. 198, p. 108298, 2021.
Crossref Google Scholar
[9]

M. Chen, Y. Wang, and X. Zhu, Few-shot website fingerprinting attack with meta-bias learning, Pattern Recognit., vol. 130, p. 108739, 2022.
Crossref Google Scholar
[10]
Y. Xu, T. Wang, Q. Li, Q. Gong, Y. Chen, and Y. Jiang, A multi-tab website fingerprinting attack, in Proc. 34th Annual Computer Security Applications Conference, San Juan, PR, USA, 2018, pp. 327–341.
Crossref
[11]

Q. Yin, Z. Liu, Q. Li, T. Wang, Q. Wang, C. Shen, and Y. Xu, An automated multi-tab website fingerprinting attack, IEEE Trans. Dependable Secure Comput., vol. 19, no. 6, pp. 3656–3670, 2022.
Crossref Google Scholar
[12]
M. Juarez, S. Afroz, G. Acar, C. Diaz, and R. Greenstadt, A critical evaluation of website fingerprinting attacks, in Proc. 2014 ACM SIGSAC Conf. Computer and Communications Security, Scottsdale, AZ, USA, 2014, pp. 263–274.
Crossref
[13]
X. Deng, Q. Yin, Z. Liu, X. Zhao, Q. Li, M. Xu, K. Xu, and J. Wu, Robust multi-tab website fingerprinting attacks in the wild, in Proc. IEEE Symp. on Security and Privacy (SP ). San Francisco, CA, USA, 2023, pp. 1005–1022.
Crossref
[14]
K. Shahbar and A. N. Zincir-Heywood, Benchmarking two techniques for tor classification: Flow level and circuit level classification, in Proc. IEEE Symp. on Computational Intelligence in Cyber Security (CICS ), Orlando, FL, USA, 2014, pp. 1–8.
Crossref
[15]

A. Montieri, D. Ciuonzo, G. Aceto, and A. Pescapé, Anonymity services tor, I2P, JonDonym: Classifying in the dark (web), IEEE Trans. Dependable Secure Comput., vol. 17, no. 3, pp. 662–675, 2020.
Crossref Google Scholar
[16]

A. Montieri, D. Ciuonzo, G. Bovenzi, V. Persico, and A. Pescapé, A dive into the dark web: Hierarchical traffic classification of anonymity tools, IEEE Trans. Netw. Sci. Eng., vol. 7, no. 3, pp. 1043–1054, 2020.
Crossref Google Scholar
[17]
B. Cetin, A. Lazar, J. Kim, A. Sim, and K. Wu, Federated wireless network intrusion detection, in Proc. IEEE Int. Conf. Big Data (Big Data ), Los Angeles, CA, USA, 2019, pp. 6004–6006.
Crossref
[18]
R. Sommer and V. Paxson, Outside the closed world: On using machine learning for network intrusion detection, in Proc. IEEE Symp. on Security and Privacy, Oakland, CA, USA, 2010, pp. 305–316.
Crossref
[19]

A. Nascita, A. Montieri, G. Aceto, D. Ciuonzo, V. Persico, and A. Pescapé, Improving performance, reliability, and feasibility in multimodal multitask traffic classification with XAI, IEEE Trans. Netw. Serv. Manag., vol. 20, no. 2, pp. 1267–1289, 2023.
Crossref Google Scholar
[20]
K. Abe and S. Goto, Fingerprinting attack on tor anonymity using deep learning, in Proc. of the APAN – Research Workshop 2016, 2016, pp. 15–20.
[21]
V. Rimmer, D. Preuveneers, M. Juarez, T. V. Goethem, and W. Joosen, Automated website fingerprinting through deep learning, in Proc. 2018 Network and Distributed System Security Symp, San Diego, CA, USA, 2018.
Crossref
[22]
T. Wang, X. Cai, R. Nithyanand, R. Johnson, and I. Goldberg, Effective attacks and provable defenses for website fingerprinting, in Proc. 23rd USENIX Security Symposium, San Diego, CA, USA, 2014, pp. 143–157.
[23]
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR ), Las Vegas, NV, USA, 2016, pp. 770–778.
Crossref
[24]
M. Juarez, M. Imani, M. Perry, C. Diaz, and M. Wright, Toward an efficient website fingerprinting defense. Lecture Notes in Computer Science. Cham, Switzerland: Springer International Publishing, 2016. pp. 27–46,
Crossref
[25]
T. Wang and I. Goldberg, Walkie-talkie: An efficient defense against passive website fingerprinting attacks, in Proc. 26th USENIX Security Symposium, Vancouver, Canada, 2017, pp. 1375–1390.
[26]

M. S. Rahman, P. Sirinam, N. Mathews, K. G. Gangadhara, and M. Wright, Tik-Tok: The utility of packet timing in website fingerprinting attacks, Proc. Priv. Enhancing Technol., vol. 2020, no. 3, pp. 5–24, 2020.
Crossref Google Scholar
[27]
W. Cui, T. Chen, C. Fields, J. Chen, A. Sierra, and E. Chan-Tin, Revisiting assumptions for website fingerprinting attacks, in Proc. 2019 ACM Asia Conf. Computer and Communications Security, Auckland, New Zealand, 2019, pp. 328–339.
Crossref
[28]
J. Long, E. Shelhamer, and T. Darrell, Fully convolutional networks for semantic segmentation, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR ), Boston, MA, USA, 2015, pp. 3431–3440.
Crossref
[29]
O. Ronneberger, P. Fischer, and T. Brox, U-Net: Convolutional networks for biomedical image segmentation, in Proc. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, Munich, Germany, 2015, pp. 234–241.
Crossref
[30]
H. Yin, Y. Liu, and Q. Chen, An elegant end-to-end fully convolutional network (E3FCN) for green tide detection using MODIS data, in Proc. 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS ), Beijing, China, 2018, pp. 1–6.
Crossref
[31]
K. Cho, B. van Merrienboer, D. Bahdanau, and Y. Bengio, On the properties of neural machine translation: Encoder–decoder approaches, in Proc. SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar, 2014.
Crossref
[32]

S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.
Crossref Google Scholar
[33]
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, arXiv preprint arXiv, p. arXiv: 1706.03762, 2017.
[34]
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, Bert: Pre-training of deep bidirectional transformers forlanguage understanding, arXiv preprint arXiv:1810.04805, 2018.
[35]
J. Gong and T. Wang, Zero-delay lightweight defenses against website fingerprinting, in Proc. 29th USENIX Security Symposium, Online, 2020, pp. 717–734.
[36]
X. Gu, M. Yang, and J. Luo, A novel Website Fingerprinting attack against multi-tab browsing behavior, in Proc. IEEE 19th Int. Conf. Computer Supported Cooperative Work in Design (CSCWD ), Calabria, Italy, 2015, pp. 234–239.
Crossref
[37]
G. Li, M. Müller, A. Thabet, and B. Ghanem, DeepGCNs: Can GCNs go As deep As CNNs? in Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV ), Seoul, Republic of Korea, 2019, pp. 9266–9275.
Crossref
[38]
G. Li, C. Xiong, A. K. Thabet, and B. Ghanem, Deeper GCN: All you need to train deeper GCNs, arXiv preprint arXiv: 2006.07739, 2020.
[39]
L.-C. Chen, A. G. Schwing, A. L. Yuille, and R. Urtasun, Learning deep structured models, arXiv preprint arXiv:1407.2538, 2014.
[40]
C. Gong, X. Tan, D. He, and T. Qin, Sentence-wisesmooth regularization for sequence to sequence learning, in Proc. 33rd AAAI Conf. Artificial Intelligence, Honolulu, HI, USA, 2019, pp. 6449–6456.
Crossref
[41]
P. Sirinam, N. Mathews, M. S. Rahman, and M. Wright, Triplet fingerprinting: More practical and portable website fingerprinting with N-shot learning, in Proc. 2019 ACM SIGSAC Conf. Computer and Communications Security, London, United Kingdom, 2019, pp. 1131–1148.
Crossref
[42]

L. Dritsoula, P. Loiseau, and J. Musacchio, A game-theoretic analysis of adversarial classification, IEEE Trans. Inf. Forensics Secur., vol. 12, no. 12, pp. 3094–3109, 2017.
Crossref Google Scholar
[43]

P. Addesso, M. Barni, M. Di Mauro, and V. Matta, Adversarial Kendall’s model towards containment of distributed cyber-threats, IEEE Trans. Inf. Forensics Secur., vol. 16, pp. 3604–3619, 2021.
Crossref Google Scholar
[44]

L. Zhang, T. Zhu, F. K. Hussain, D. Ye, and W. Zhou, A game-theoretic method for defending against advanced persistent threats in cyber systems, IEEE Trans. Inf. Forensics Secur., vol. 18, pp. 1349–1364, 2022.
Crossref Google Scholar
[45]
C.-H. He, S.-C. Lai, and K.-M. Lam, Improving object detection with relation graph inference, in Proc. ICASSP 2019 - 2019 IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP ), Brighton, UK, 2019, pp. 2537–2541.
Crossref
[46]
D. Xu, Y. Zhu, C. B. Choy, and F.-F. Li, Scene graph generation by iterative message passing, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR ), Honolulu, HI, USA, 2017, pp. 3097–3106.
Crossref
[47]
J. Yang, J. Lu, S. Lee, D. Batra, and D. Parikh, Graph R-CNN for scene graph generation. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018. pp. 690–706.
Crossref
Tsinghua Science and Technology
Volume 30 Issue 2,
April 2025
Pages 830-850
DOI: 10.26599/TST.2024.9010073
Cite this article:
Yin H, Liu Y, Guo Z, et al. From Traces to Packets: Realistic Deep Learning Based Multi-Tab Website Fingerprinting Attacks. Tsinghua Science and Technology, 2025, 30(2): 830-850. https://doi.org/10.26599/TST.2024.9010073

436

Views

65

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 02 December 2023
Revised: 10 March 2024
Accepted: 13 April 2024
Published: 09 December 2024
© The Author(s) 2025.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return