SpectAcle : Fault Localisation of AI-Enabled CPS by Exploiting Sequences of DNN Controller Inferences

Cyber-Physical Systems (CPSs) are increasingly adopting deep neural networks (DNNs) as controllers, giving birth to AI-enabled CPSs . Despite their advantages, many concerns arise about the safety of DNN controllers. Numerous efforts have been made to detect system executions that violate safety specifications; however, once a violation is detected, to fix the issue, it is necessary to localise the parameters of the DNN controller responsible for the wrong decisions leading to the violation. This is particularly challenging, as it requires to consider a sequence of control decisions, rather than a single one, preceding the violation. To tackle this problem, we propose

, that can localise the faulty parameters in DNN controllers. considers the DNN inferences preceding the specification violation and uses forward impact to determine the DNN parameters that are more relevant to the DNN outputs. Then, it identifies which of these parameters are responsible for the specification violation, by adapting classic suspiciousness metrics. Moreover, we propose two versions of , that consider differently the timestamps that precede the specification violation. We experimentally evaluate the effectiveness of on 6067 faulty benchmarks, spanning over different application domains. The results show that can detect most of the faults.