TONet: A Fast and Efficient Method for Traffic Obfuscation Using Adversarial Machine Learning

Fan Yang; Bingyang Wen; Cristina Comaniciu; K. P. Subbalakshmi; R. Chandramouli

doi:10.1109/LCOMM.2022.3195685

TONet: A Fast and Efficient Method for Traffic Obfuscation Using Adversarial Machine Learning

Fan Yang, Bingyang Wen, Cristina Comaniciu, K. P. Subbalakshmi, R. Chandramouli

Department of Electrical and Computer Engineering

Stevens Institute of Technology

Research output: Contribution to journal › Article › peer-review

Abstract

In this letter, we address the problem of privacy leakage in communications based on analysis of traffic patterns. We propose an efficient method of traffic obfuscation based on neural networks, that generates traffic distortions with minimal overhead and computational cost. Our experimental results show that the proposed method is orders of magnitude faster in implementation and has a higher obfuscation success rate with less perturbation on the traffic samples, compared to previously proposed adversarial machine learning-based traffic obfuscation methods.

Original language	English
Pages (from-to)	2537-2541
Number of pages	5
Journal	IEEE Communications Letters
Volume	26
Issue number	11
DOIs	https://doi.org/10.1109/LCOMM.2022.3195685
State	Published - Nov 1 2022

ASJC Scopus subject areas

Modeling and Simulation
Computer Science Applications
Electrical and Electronic Engineering

Keywords

Traffic type obfuscation
adversarial learning
privacy leakage
security

Access to Document

10.1109/LCOMM.2022.3195685

Cite this

@article{8597ab64ed904da19952bca269a69725,

title = "TONet: A Fast and Efficient Method for Traffic Obfuscation Using Adversarial Machine Learning",

abstract = "In this letter, we address the problem of privacy leakage in communications based on analysis of traffic patterns. We propose an efficient method of traffic obfuscation based on neural networks, that generates traffic distortions with minimal overhead and computational cost. Our experimental results show that the proposed method is orders of magnitude faster in implementation and has a higher obfuscation success rate with less perturbation on the traffic samples, compared to previously proposed adversarial machine learning-based traffic obfuscation methods.",

keywords = "Traffic type obfuscation, adversarial learning, privacy leakage, security",

author = "Fan Yang and Bingyang Wen and Cristina Comaniciu and Subbalakshmi, {K. P.} and R. Chandramouli",

note = "Publisher Copyright: {\textcopyright} 1997-2012 IEEE.",

year = "2022",

month = nov,

day = "1",

doi = "10.1109/LCOMM.2022.3195685",

language = "English",

volume = "26",

pages = "2537--2541",

journal = "IEEE Communications Letters",

issn = "1089-7798",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "11",

}

TY - JOUR

T1 - TONet

T2 - A Fast and Efficient Method for Traffic Obfuscation Using Adversarial Machine Learning

AU - Yang, Fan

AU - Wen, Bingyang

AU - Comaniciu, Cristina

AU - Subbalakshmi, K. P.

AU - Chandramouli, R.

PY - 2022/11/1

Y1 - 2022/11/1

N2 - In this letter, we address the problem of privacy leakage in communications based on analysis of traffic patterns. We propose an efficient method of traffic obfuscation based on neural networks, that generates traffic distortions with minimal overhead and computational cost. Our experimental results show that the proposed method is orders of magnitude faster in implementation and has a higher obfuscation success rate with less perturbation on the traffic samples, compared to previously proposed adversarial machine learning-based traffic obfuscation methods.

AB - In this letter, we address the problem of privacy leakage in communications based on analysis of traffic patterns. We propose an efficient method of traffic obfuscation based on neural networks, that generates traffic distortions with minimal overhead and computational cost. Our experimental results show that the proposed method is orders of magnitude faster in implementation and has a higher obfuscation success rate with less perturbation on the traffic samples, compared to previously proposed adversarial machine learning-based traffic obfuscation methods.

KW - Traffic type obfuscation

KW - adversarial learning

KW - privacy leakage

KW - security

UR - http://www.scopus.com/inward/record.url?scp=85135737144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85135737144&partnerID=8YFLogxK

U2 - 10.1109/LCOMM.2022.3195685

DO - 10.1109/LCOMM.2022.3195685

M3 - Article

SN - 1089-7798

VL - 26

SP - 2537

EP - 2541

JO - IEEE Communications Letters

JF - IEEE Communications Letters

IS - 11

ER -

TONet: A Fast and Efficient Method for Traffic Obfuscation Using Adversarial Machine Learning

Abstract

ASJC Scopus subject areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this