DO CAN INTRUSION DETECTORS TRAVEL? A CROSS-DATASET AND ZERO-DAY STUDY WITH IDENTIFIER-AGNOSTIC, LOCALLY CALIBRATED ENSEMBLES
Intrusion detection systems (IDS) for the vehicular CAN bus that use Machine Learning are usually evaluated and reported to achieve very high detection accuracy, commonly above 99%, on random splits of a single dataset. We test and reproduce such high detection accuracy for four publicly available CAN IDS benchmark cor...