Active vs. Passive: A Comparison of Automata Learning Paradigms for Network Protocols

TL;DR

This paper compares active and passive automata learning methods for network protocols, showing passive learning can be more data-efficient but more costly in data generation, with implications for practical protocol analysis.

Contribution

It provides an empirical comparison of active versus passive automata learning for BLE and MQTT protocols, highlighting the trade-offs in data efficiency and generation costs.

Findings

Passive learning requires less data than active learning for accurate models.

Passive data generation can be more expensive than active interaction.

Passive techniques are promising when active interfaces are impractical.

Abstract

Active automata learning became a popular tool for the behavioral analysis of communication protocols. The main advantage is that no manual modeling effort is required since a behavioral model is automatically inferred from a black-box system. However, several real-world applications of this technique show that the overhead for the establishment of an active interface might hamper the practical applicability. Our recent work on the active learning of Bluetooth Low Energy (BLE) protocol found that the active interaction creates a bottleneck during learning. Considering the automata learning toolset, passive learning techniques appear as a promising solution since they do not require an active interface to the system under learning. Instead, models are learned based on a given data set. In this paper, we evaluate passive learning for two network protocols: BLE and Message Queuing Telemetry Transport (MQTT). Our results show that passive techniques can correctly learn with less data than required by active learning. However, a general random data generation for passive learning is more expensive compared to the costs of active learning.