FBI: Fingerprinting models with Benign Inputs. (arXiv:2208.03169v1 [cs.CR])

Recent advances in the fingerprinting of deep neural networks detect
instances of models, placed in a black-box interaction scheme. Inputs used by
the fingerprinting protocols are specifically crafted for each precise model to
be checked for. While efficient in such a scenario, this nevertheless results
in a lack of guarantee after a mere modification (like retraining,
quantization) of a model. This paper tackles the challenges to propose i)
fingerprinting schemes that are resilient to significant modifications of the
models, by …

arxiv fbi