AWEncoder: Adversarial Watermarking Pre-Trained Encoders in Contrastive Learning

As a self-supervised learning paradigm, contrastive learning has been widely used to pre-train a powerful encoder as an effective feature extractor for various downstream tasks. This process requires numerous unlabeled training data and computational resources, which makes the pre-trained encoder be...

Cijeli opis

Bibliografski detalji

Glavni autori:	Tianxing Zhang, Hanzhou Wu, Xiaofeng Lu, Gengle Han, Guangling Sun
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2023-03-01
Serija:	Applied Sciences
Teme:	model watermarking contrastive learning security deep neural networks
Online pristup:	https://www.mdpi.com/2076-3417/13/6/3531
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!