NNReArch: A Tensor Program Scheduling Framework Against Neural Network Architecture Reverse Engineering. (arXiv:2203.12046v1 [cs.CR])

Architecture reverse engineering has become an emerging attack against deep
neural network (DNN) implementations. Several prior works have utilized
side-channel leakage to recover the model architecture while the target is
executing on a hardware acceleration platform. In this work, we target an
open-source deep-learning accelerator, Versatile Tensor Accelerator (VTA), and
utilize electromagnetic (EM) side-channel leakage to comprehensively learn the
association between DNN architecture configurations and EM emanations. We also
consider the holistic system -- including the low-level tensor program code …

architecture engineering framework network neural network program reverse reverse engineering tensor