TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning

arXiv cs.AI / 4/6/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces TRACE, an ML pipeline that detects Internet route changes using only traceroute latency data, avoiding dependence on control-plane information.
It applies a feature-engineering approach using rolling statistics and aggregated temporal/context patterns to capture the dynamics of routing changes.
TRACE uses a stacked ensemble of Gradient Boosted Decision Trees with a hyperparameter-optimized meta-learner to improve classification accuracy.
The method calibrates decision thresholds to handle rare-event class imbalance, yielding higher F1-score than traditional baseline models.
The authors report effective performance for real-world Internet routing change detection, emphasizing robustness under endpoint active measurement constraints.

Abstract

Detecting Internet routing instability is a critical yet challenging task, particularly when relying solely on endpoint active measurements. This study introduces TRACE, a MachineLearning (ML)pipeline designed to identify route changes using only traceroute latency data, thereby ensuring independence from control plane information. We propose a robust feature engineering strategy that captures temporal dynamics using rolling statistics and aggregated context patterns. The architecture leverages a stacked ensemble of Gradient Boosted Decision Trees refined by a hyperparameter-optimized meta-learner. By strictly calibrating decision thresholds to address the inherent class imbalance of rare routing events, TRACE achieves a superior F1-score performance, significantly outperforming traditional baseline models and demonstrating strong effective ness in detecting routing changes on the Internet.