AVA: Automated interpretation of dynamically detected anomalies

Dynamic analysis techniques have been extensively adopted to discover causes of observed failures. In particular, anomaly detection techniques can infer behavioral models from observed legal executions and compare failing executions with the inferred models to automatically identify the likely anomalous events that caused observed failures. Unfortunately the output of these techniques is limited to a set of independent suspicious anomalous events that does not capture the structure and the rationale of the differences between the correct and the failing executions. Thus, testers spend a relevant amount of time and effort to investigate executions and interpret these differences, reducing effectiveness of anomaly detection techniques. In this paper, we present Automata Violations Analyzer (AVA), a technique to automatically produce candidate interpretations of detected failures from anomalies identified by anomaly detection techniques. Interpretations capture the rationale of the differences between legal and failing executions with user understandable patterns that simplify identification of failure causes. The empirical validation with synthetic cases and third-party systems shows that AVA produces useful interpretations