Anomaly Detection in Automobile Control Network Data with Long Short-Term Memory Networks

Modern automobiles have been proven vulnerable to hacking by security researchers. By exploiting vulnerabilities in the car's external interfaces, such as wifi, bluetooth, and physical connections, they can access a car's controller area network (CAN) bus. On the CAN bus, commands can be sent to control the car, for example cutting the brakes or stopping the engine. While securing the car's interfaces to the outside world is an important part of mitigating this threat, the last line of defence is detecting malicious behaviour on the CAN bus. We propose an anomaly detector based on a Long Short-Term Memory neural network to detect CAN bus attacks. The detector works by learning to predict the next data word originating from each sender on the bus. Highly surprising bits in the actual next word are flagged as anomalies. We evaluate the detector by synthesizing anomalies with modified CAN bus data. The synthesized anomalies are designed to mimic attacks reported in the literature. We show that the detector can detect anomalies we synthesized with low false alarm rates. Additionally, the granularity of the bit predictions can provide forensic investigators clues as to the nature of flagged anomalies.

I. Introduction

Automobiles have evolved from purely mechanical devices to connected computing platforms. Historically the computers in cars were isolated from the outside world, and the security of those systems was not of concern. But in recent years it has become clear that this is no longer the case; hackers have demonstrated that cars are vulnerable to cyber attacks. Such attacks work by leveraging weaknesses in the Electronic Control Units (ECUs) that control the vehicle. The ECUs communicate using the Controller Area Network (CAN) bus standard. In order to control the car, hackers typically gain access through an external interface such as cellular, bluetooth, or devices plugged into the onboard diagnostic port [1], [2]. Once they have gained a foothold, they find a way to transmit packets on the CAN bus crafted to cause specific effects. ECUs will in most cases accept properly formatted packets without authentication, making it is relatively easy to control the vehicle [3], [4]. However, any attack will modify the CAN bus traffic, and such modifications can be detected.