Feasibility of State Space Models for Network Traffic Generation

TL;DR

This paper explores the use of state-space models, particularly Mamba, for generating synthetic network traffic that closely resembles real data, addressing limitations in existing methods due to privacy and data quality issues.

Contribution

It introduces the application of state-space models to network traffic generation and demonstrates their superior statistical similarity to real traffic compared to existing methods.

Findings

State-space models can generate traffic with higher statistical similarity to real data.

Mamba outperforms current state-of-the-art traffic generators.

Synthetic traces are potentially useful for various network analysis tasks.

Abstract

Many problems in computer networking rely on parsing collections of network traces (e.g., traffic prioritization, intrusion detection). Unfortunately, the availability and utility of these collections is limited due to privacy concerns, data staleness, and low representativeness. While methods for generating data to augment collections exist, they often fall short in replicating the quality of real-world traffic In this paper, we i) survey the evolution of traffic simulators/generators and ii) propose the use of state-space models, specifically Mamba, for packet-level, synthetic network trace generation by modeling it as an unsupervised sequence generation problem. Early evaluation shows that state-space models can generate synthetic network traffic with higher statistical similarity to real traffic than the state-of-the-art. Our approach thus has the potential to reliably generate realistic, informative synthetic network traces for downstream tasks.