DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking. (arXiv:2207.13321v1 [cs.CR])

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. In this work, we propose
a novel watermarking technique called DynaMarks to protect the intellectual
property (IP) of DL models against such model extraction attacks in a black-box
setting. Unlike existing approaches, DynaMarks does not alter the training
process of the original model but rather embeds watermark …

deep learning dynamic