Design of countermeasure to packet falsification in vehicle platooning by explainable artificial intelligence

In view of system reliability, extraction of knowledge from models of artificial intelligence may be more important than their forecasting ability. The elaboration of rules found by explainable artificial intelligence gives here insight into the problem of packet falsification in vehicle platooning. Detection and countermeasure are designed on the basis of feature and value ranking as well as rule confidence and they are validated under a large range of working conditions. The certification of safe operating conditions is found by achieving (statistically) zero false negatives, namely, the operating conditions predicted as ‘safe’ never lead to collision despite the cyber attack.