On the Limitations of Model Stealing with Uncertainty Quantification Models

no code implementations • 9 May 2023 • David Pape, Sina Däubener, Thorsten Eisenhofer, Antonio Emanuele Cinà, Lea Schönherr

We realize that during training, the models tend to have similar predictions, indicating that the network diversity we wanted to leverage using uncertainty quantification models is not (high) enough for improvements on the model stealing task.

Uncertainty Quantification