Work-in-Progress: Road Context-Aware Intrusion Detection System for Autonomous Cars

Abstract

The necessity of intrusion detection system (IDS) is concrete for automobiles, and is particularly critical for unmanned, autonomous ones. However, limited work has been done to detect intrusions in an autonomous car while existing IDSs have limitations against strong adversaries. We hence consider the very nature of autonomous car and propose to utilize the road context to build a Road context-aware IDS (RAIDS). We hypothesize that given a computer-controlled car, the pattern and data of frames transmitted on the in-vehicle communication network should be relatively regular and obtainable when the car is cruising through continuous road contexts. Accordingly we design RAIDS and implement a preliminary prototype that discerns and identifies anomalous frames fabricated or suspended by adversaries. Evaluation results show that RAIDS effectively detects intrusions that are beyond the capabilities of state-of-the-art IDS.