Rema Hanna and Shing-Yi Wang give us evidence from India:
we demonstrate that university students who cheat on a simple task in a laboratory setting are more likely to state a preference for entering public service.
…we also show that cheating on this task is predictive of corrupt behavior by real government workers
A hypothesis for their next study: The university students who change the rules so that their cheating is not technically illegal? They go into finance.