# TempoNet: Learning Realistic Communication and Timing Patterns for Network Traffic Simulation

Source: [TempoNet: Learning Realistic Communication and Timing Patterns for Network Traffic Simulation](<https://www.sota2.com/research/paper/6973006eb2be0ed85a78c8ef>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-24T05:00:05.231Z

Authors: Kristen Moore, Diksha Goel, Cody James Christopher, Zhen Wang, Minjune Kim, Ahmed Ibrahim, Ahmad Mohsin, Seyit Camtepe

Published: 2026-01-22T05:23:19.000Z

## Abstract

Realistic network traffic simulation is critical for evaluating intrusion detection systems, stress-testing network protocols, and constructing high-fidelity environments for cybersecurity training. While attack traffic can often be layered into training environments using red-teaming or replay methods, generating authentic benign background traffic remains a core challenge -- particularly in simulating the complex temporal and communication dynamics of real-world networks. This paper introduces TempoNet, a novel generative model that combines multi-task learning with multi-mark temporal point processes to jointly model inter-arrival times and all packet- and flow-header fields. TempoNet captures fine-grained timing patterns and higher-order correlations such as host-pair behavior and seasonal trends, addressing key limitations of GAN-, LLM-, and Bayesian-based methods that fail to reproduce structured temporal variation. TempoNet produces temporally consistent, high-fidelity traces, validated on real-world datasets. Furthermore, we show that intrusion detection models trained on TempoNet-generated background traffic perform comparably to those trained on real data, validating its utility for real-world security applications.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Network Traffic Generation on CIDDS (test)](<https://www.sota2.com/research/sota/network-traffic-generation-on-cidds-test.md>): Network Traffic Generation; CIDDS (test); CMD: 0.043.

- [Intrusion Detection on CIDDS](<https://www.sota2.com/research/sota/intrusion-detection-on-cidds.md>): Intrusion Detection; CIDDS; Benign F1: 98.

- [Network Traffic Generation on LANL (test)](<https://www.sota2.com/research/sota/network-traffic-generation-on-lanl-test.md>): Network Traffic Generation; LANL (test); CMD: 0.043.

- [Network Traffic Generation on DC (test)](<https://www.sota2.com/research/sota/network-traffic-generation-on-dc-test.md>): Network Traffic Generation; DC (test); CMD: 0.074.

- [Network Traffic Generation on ToN\_IoT (test)](<https://www.sota2.com/research/sota/network-traffic-generation-on-ton_iot-test.md>): Network Traffic Generation; ToN\_IoT (test); CMD: 0.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.15663>)

[PDF](<https://arxiv.org/pdf/2601.15663.pdf>)
