DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking

no code implementations • 27 Jul 2022 • Abhishek Chakraborty, Daniel Xing, Yuntao Liu, Ankur Srivastava

The functionality of a deep learning (DL) model can be stolen via model extraction where an attacker obtains a surrogate model by utilizing the responses from a prediction API of the original model.

Model extraction