StegGuard: Fingerprinting Self-supervised Pre-trained Encoders via Secrets Embeder and Extractor. (arXiv:2310.03380v1 [cs.CR])

In this work, we propose StegGuard, a novel fingerprinting mechanism to
verify the ownership of the suspect pre-trained encoder using steganography. A
critical perspective in StegGuard is that the unique characteristic of the
transformation from an image to an embedding, conducted by the pre-trained
encoder, can be equivalently exposed how an embeder embeds secrets into images
and how an extractor extracts the secrets from encoder's embeddings with a
tolerable error after the secrets are subjected to the encoder's
transformation. While …

critical fingerprinting image mechanism novel ownership perspective secrets steganography transformation verify work