To identify general principles, researchers are increasingly interested insurveying largecollections ofnetworks that are trained on, or biologically adapted to,similar tasks.

Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generationAPIs,recentworkhasintroduced awatermarking algorithm andutilized the null-hypothesis test as a post-hoc ownership verification on the imitation models.