StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning. (arXiv:2201.05889v2 [cs.CR] UPDATED)

Pre-trained encoders are general-purpose feature extractors that can be used
for many downstream tasks. Recent progress in self-supervised learning can
pre-train highly effective encoders using a large volume of unlabeled data,
leading to the emerging encoder as a service (EaaS). A pre-trained encoder may
be deemed confidential because its training requires lots of data and
computation resources as well as its public release may facilitate misuse of
AI, e.g., for deepfakes generation. In this paper, we propose the first attack …

stealing