When NAS Meets Watermarking: Ownership Verification of DNN Models via Cache Side Channels
share
We present a novel watermarking scheme to verify the ownership of DNN models. Existing solutions embedded watermarks into the model parameters, which were proven to be removable and detectable by an adversary to invalidate the protection. In contrast, we propose to implant watermarks into the model architectures. We design new algorithms based on Neural Architecture Search (NAS) to generate watermarked architectures, which are unique enough to represent the ownership, while maintaining high model usability. We further leverage cache side channels to extract and verify watermarks from the black-box models at inference. Theoretical analysis and extensive evaluations show our scheme has negligible impact on the model performance, and exhibits strong robustness against various model transformations.
READ FULL TEXT