Abstract
In this paper, we introduce a novel traffic masking method, called Generative Adversarial Network (GAN) tunnel, to protect the identity of applications that generate network traffic from classification by adversarial Internet traffic classifiers (ITCs). Such ITCs have been used in the past for website fingerprinting and detection of network protocols. Their use is becoming more ubiquitous than before for inferring user information. ITCs based on machine learning can identify user applications by analyzing the statistical features of encrypted packets. Our proposed GAN tunnel generates traffic that mimics a decoy application and encapsulates actual user traffic in the GAN-generated traffic to prevent classification from adversarial ITCs. We show that the statistical distributions of the generated traffic features closely resemble those of the actual network traffic. Therefore, the actual user applications and information associated with the user remain anonymous. We test the GAN tunnel traffic against high-performing ITCs, such as Random Forest and eXtreme Gradient Boosting (XGBoost), and we show that the GAN tunnel protects the identity of the source applications effectively.
Highlights
Internet traffic classifiers (ITCs) use the extracted statistical data from packets of a network to classify them and infer information from them [1], [2]
After calculating the Wasserstein-1 values as shown in Figure 4, we further evaluate the performance of our Wasserstein GAN (WGAN) by comparing the distributions of generated features with those of the actual network traffic
We later show that the small discrepancy of OneNote interarrival times between the actual and generated traffic distributions does not affect the performance of the WGAN tunnel against adversarial ITCs
Summary
Internet traffic classifiers (ITCs) use the extracted statistical data from packets of a network to classify them and infer information from them [1], [2]. There is a need for a method that can circumvent packet classification by obfuscating a holistic traffic profile To address this need, we propose using a generative adversarial network (GAN) model [20] to design a method that holistically modifies statistical traffic features to circumvent classification. We use the generated flows to encapsulate and transmit the actual traffic with protected privacy against adversarial ITCs, as a tunnel The main contributions of this paper are: We 1) design a network traffic generator based on GAN, 2) propose a novel GAN tunnel method to protect user traffic from classification, 3) demonstrate that the GAN tunnel traffic is effective in anonymizing the traffic against different ITCs. To best of our knowledge, this is the first work that proposes the use of a GAN for tunneling network traffic.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
