Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NetDPSyn: Synthesizing Network Traces under Differential Privacy

Danyu Sun, Joann Qiongna Chen, Chen Gong, Tianhao Wang, Zhou Li

TL;DR

NetDPSyn is introduced, the first system to synthesize high-fidelity network traces under privacy guarantees and is built with the Differential Privacy (DP) framework as its core, which is significantly different from prior works that apply DP when training the generative model.

Abstract

As the utilization of network traces for the network measurement research becomes increasingly prevalent, concerns regarding privacy leakage from network traces have garnered the public's attention. To safeguard network traces, researchers have proposed the trace synthesis that retains the essential properties of the raw data. However, previous works also show that synthesis traces with generative models are vulnerable under linkage attacks. This paper introduces NetDPSyn, the first system to synthesize high-fidelity network traces under privacy guarantees. NetDPSyn is built with the Differential Privacy (DP) framework as its core, which is significantly different from prior works that apply DP when training the generative model. The experiments conducted on three flow and two packet datasets indicate that NetDPSyn achieves much better data utility in downstream tasks like anomaly detection. NetDPSyn is also 2.5 times faster than the other methods on average in data synthesis.

NetDPSyn: Synthesizing Network Traces under Differential Privacy

TL;DR

NetDPSyn is introduced, the first system to synthesize high-fidelity network traces under privacy guarantees and is built with the Differential Privacy (DP) framework as its core, which is significantly different from prior works that apply DP when training the generative model.

Abstract

As the utilization of network traces for the network measurement research becomes increasingly prevalent, concerns regarding privacy leakage from network traces have garnered the public's attention. To safeguard network traces, researchers have proposed the trace synthesis that retains the essential properties of the raw data. However, previous works also show that synthesis traces with generative models are vulnerable under linkage attacks. This paper introduces NetDPSyn, the first system to synthesize high-fidelity network traces under privacy guarantees. NetDPSyn is built with the Differential Privacy (DP) framework as its core, which is significantly different from prior works that apply DP when training the generative model. The experiments conducted on three flow and two packet datasets indicate that NetDPSyn achieves much better data utility in downstream tasks like anomaly detection. NetDPSyn is also 2.5 times faster than the other methods on average in data synthesis.
Paper Structure (24 sections, 2 equations, 8 figures, 7 tables, 1 algorithm)

This paper contains 24 sections, 2 equations, 8 figures, 7 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Network Dataset and Privacy
  4. Differential Privacy
  5. Related Works
  6. Threat Model
  7. NetDPSyn
  8. Motivation and Workflow
  9. Pre-processing
  10. Generating Noisy Marginal Tables
  11. Record Synthesis
  12. Evaluation
  13. Experimental Setup
  14. Data Sketching
  15. Machine-learning Tasks
  16. ...and 9 more sections

Figures (8)

  • Figure 1: High-level workflow of NetDPSyn.
  • Figure 2: Relative error of various sketch algorithms. The lower the better.
  • Figure 3: Classification accuracy of three flow datasets. The higher the better.
  • Figure 4: NetML results on two packet datasets. The lower the better.
  • Figure 5: TON (NetFlow) JSD and EMD. The lower the better.
  • ...and 3 more figures