Extending Attack-Fault Trees with Runtime Verification

Abstract

Autonomous systems are often complex and prone to software failures and cyber-attacks. We introduce RVAFTs, an extension of Attack-Fault Trees (AFTs) with runtime events that can be used to construct runtime monitors. These monitors are able to detect when failures, that can be caused either by an attack or by a fault, occur. The safety and security properties monitored are, in turn, derived from the hierarchical decomposition of RVAFTs. Our approach not only provides further use of AFTs, but also improves the process of instrumentation often required in runtime verification. We explain the principles and provide a simple case study demonstrating how RVAFTs can be used in practice. Through this we are also able to evaluate the detection of faults and attacks as well as assessing the computational overhead of the monitors.