# Chocolatine: Outage Detection for Internet Background Radiation

**Authors:** Andreas Guillot, Romain Fontugne, Philipp Winter, Pascal Merindol,, Alistair King, Alberto Dainotti, Cristel Pelsser

arXiv: 1906.04426 · 2019-10-01

## TL;DR

Chocolatine is a novel outage detection method leveraging Internet Background Radiation and Seasonal ARIMA modeling to identify remote connectivity issues with high accuracy, outperforming existing techniques.

## Contribution

The paper introduces Chocolatine, a new IBR-based outage detection approach using seasonal modeling, providing a simple, efficient, and more accurate solution than prior methods.

## Key findings

- Achieves 90% true-positive rate and 2% false-positive rate.
- Outperforms CAIDA's existing IBR-based detection method.
- Detects outages also identified by BGP and active probing methods.

## Abstract

The Internet is a complex ecosystem composed of thousands of Autonomous Systems (ASs) operated by independent organizations; each AS having a very limited view outside its own network. These complexities and limitations impede network operators to finely pinpoint the causes of service degradation or disruption when the problem lies outside of their network. In this paper, we present Chocolatine, a solution to detect remote connectivity loss using Internet Background Radiation (IBR) through a simple and efficient method. IBR is unidirectional unsolicited Internet traffic, which is easily observed by monitoring unused address space. IBR features two remarkable properties: it is originated worldwide, across diverse ASs, and it is incessant. We show that the number of IP addresses observed from an AS or a geographical area follows a periodic pattern. Then, using Seasonal ARIMA to statistically model IBR data, we predict the number of IPs for the next time window. Significant deviations from these predictions indicate an outage. We evaluated Chocolatine using data from the UCSD Network Telescope, operated by CAIDA, with a set of documented outages. Our experiments show that the proposed methodology achieves a good trade-off between true-positive rate (90%) and false-positive rate (2%) and largely outperforms CAIDA's own IBR-based detection method. Furthermore, performing a comparison against other methods, i.e., with BGP monitoring and active probing, we observe that Chocolatine shares a large common set of outages with them in addition to many specific outages that would otherwise go undetected.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/1906.04426/full.md

## Figures

6 figures with captions in the complete paper: https://tomesphere.com/paper/1906.04426/full.md

## References

32 references — full list in the complete paper: https://tomesphere.com/paper/1906.04426/full.md

---
Source: https://tomesphere.com/paper/1906.04426