Introducing Alias Information into Model-Based Debugging

Model-based diagnosis applied to computer programs has been studied for several years. Although there are still weaknesses in the used models, especially on dealing with dynamic data structures, the approach has been proven useful for automatic debugging. The weaknesses stem from the fact that heap objects are modeled without considering alias information. Our approach extends the modeling process with a static points-to analysis that reveals the structure and relations between heap objects. This points-to information is then used to improve existing value-based models for Java programs such that the diagnosis engine is able to differentiate between separate data structures. With this extension the set of diagnoses can be reduced for certain types of programs.