SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders. (arXiv:2201.11692v1 [cs.CR])

Web: http://arxiv.org/abs/2201.11692

Self-supervised learning is an emerging machine learning (ML) paradigm.
Compared to supervised learning that leverages high-quality labeled datasets to
achieve good performance, self-supervised learning relies on unlabeled datasets
to pre-train powerful encoders which can then be treated as feature extractors
for various downstream tasks. The huge amount of data and computational
resources consumption makes the encoders themselves become a valuable
intellectual property of the model owner. Recent research has shown that the ML
model's copyright is threatened by model stealing …

arxiv learning self-supervised learning supervised learning