Hardware Fingerprinting for the ARINC 429 Avionic Bus

TL;DR

This paper introduces a hardware fingerprinting-based intrusion detection system for ARINC 429 avionics data buses, enabling rapid detection of rogue devices without protocol modifications.

Contribution

It presents the first hardware fingerprinting approach for ARINC 429, capable of detecting hardware switches in real-time using analog signal properties.

Findings

Detects rogue transmitters in under 50ms

Detects rogue receivers in under 3 seconds

Achieves near-zero false alarms

Abstract

ARINC 429 is the most common data bus in use today in civil avionics. However, the protocol lacks any form of source authentication. A technician with physical access to the bus is able to replace a transmitter by a rogue device, and the receivers will accept its malicious data as they have no method of verifying the authenticity of messages. Updating the protocol would close off security loopholes in new aircraft but would require thousands of airplanes to be modified. For the interim, until the protocol is replaced, we propose the first intrusion detection system that utilizes a hardware fingerprinting approach for sender identification for the ARINC 429 data bus. Our approach relies on the observation that changes in hardware, such as replacing a transmitter or a receiver with a rogue one, modify the electric signal of the transmission. Because we rely on the analog properties, and not on the digital content of the transmissions, we are able to detect a hardware switch as soon as it occurs, even if the data that is being transmitted is completely normal. Thus, we are able to preempt the attack before any damage is caused. In this paper we describe the design of our intrusion detection system and evaluate its performance against different adversary models. Our analysis includes both a theoretical Markov-chain model and an extensive empirical evaluation. For this purpose, we collected a data corpus of ARINC 429 data traces, which may be of independent interest since, to the best of our knowledge, no public corpus is available. We find that our intrusion detection system is quite realistic: e.g., it achieves near-zero false alarms per second, while detecting a rogue transmitter in under 50ms, and detecting a rogue receiver in under 3 seconds. In other words, technician attacks can be reliably detected during the pre-flight checks, well before the aircraft takes off.