# DeePCCI: Deep Learning-based Passive Congestion Control Identification

## TL;DR

DeePCCI is a deep learning method for passive identification of congestion control variants using only packet arrival data, applicable to encrypted traffic and adaptable to new protocols like QUIC.

## Contribution

It introduces a domain-knowledge-free, deep learning-based approach for passive congestion control identification that works with encrypted traffic and does not rely on outdated assumptions.

## Key findings

- Accurately identifies congestion control variants from packet arrival data.
- Works effectively on encrypted traffic without needing transport headers.
- Extensible to protocols like QUIC.

## Abstract

Transport protocols use congestion control to avoid overloading a network. Nowadays, different congestion control variants exist that influence performance. Studying their use is thus relevant, but it is hard to identify which variant is used. While passive identification approaches exist, these require detailed domain knowledge and often also rely on outdated assumptions about how congestion control operates and what data is accessible. We present DeePCCI, a passive, deep learning-based congestion control identification approach which does not need any domain knowledge other than training traffic of a congestion control variant. By only using packet arrival data, it is also directly applicable to encrypted (transport header) traffic. DeePCCI is therefore more easily extendable and can also be used with QUIC.