SEEK: model extraction attack against hybrid secure inference protocols. (arXiv:2209.06373v1 [cs.CR])

Web: http://arxiv.org/abs/2209.06373

Security concerns about a machine learning model used in a
prediction-as-a-service include the privacy of the model, the query and the
result. Secure inference solutions based on homomorphic encryption (HE) and/or
multiparty computation (MPC) have been developed to protect all the sensitive
information. One of the most efficient type of solution utilizes HE for linear
layers, and MPC for non-linear layers. However, for such hybrid protocols with
semi-honest security, an adversary can malleate the intermediate features in
the inference process, …

attack hybrid protocols