Learning state machines from infrequent software traces (VIDI – TTW)

Software leaves many traces of network packets, system calls, and warning or error statements, called logs. Software analysts study these logs to find programming errors and other issues. Machine learning techniques can be used to automate this analysis. When applied to software logs, they learn models of the software’s known frequent behaviour and discard the infrequent data containing important errors as noise, making the learned models uninteresting for analysis. We research novel machine learning algorithms and develop tools for learning from software log data. Our aim is to provide software analysts with a useful and understandable model. Our focus is on learning state machines from traces that occur infrequently.es to tell.

Contact person: Dr. Sicco Verwer