INDRA: Intrusion Detection using Recurrent Autoencoders in Automotive Embedded Systems

TL;DR

This paper introduces INDRA, an intrusion detection system for automotive embedded systems that uses recurrent autoencoders to identify anomalies in CAN bus communications, enhancing vehicle security.

Contribution

The paper presents a novel GRU-based recurrent autoencoder framework for anomaly detection in automotive CAN bus systems, improving security measures.

Findings

INDRA effectively detects various attack scenarios.

Compared to prior works, INDRA shows improved detection accuracy.

The framework demonstrates robustness across different attack types.

Abstract

Today's vehicles are complex distributed embedded systems that are increasingly being connected to various external systems. Unfortunately, this increased connectivity makes the vehicles vulnerable to security attacks that can be catastrophic. In this work, we present a novel Intrusion Detection System (IDS) called INDRA that utilizes a Gated Recurrent Unit (GRU) based recurrent autoencoder to detect anomalies in Controller Area Network (CAN) bus-based automotive embedded systems. We evaluate our proposed framework under different attack scenarios and also compare it with the best known prior works in this area.