Hufu: A Modality-Agnositc Watermarking System for Pre-Trained Transformers via Permutation Equivariance

arXiv:2403.05842v1 Announce Type: new
Abstract: With the blossom of deep learning models and services, it has become an imperative concern to safeguard the valuable model parameters from being stolen. Watermarking is considered an important tool for ownership verification. However, current watermarking schemes are customized for different models and tasks, hard to be integrated as an integrated intellectual protection service. We propose Hufu, a modality-agnostic watermarking system for pre-trained Transformer-based models, relying on the permutation equivariance property of Transformers. Hufu embeds …

arxiv cs.ai cs.cr current deep learning important ownership safeguard services stolen system tool transformers verification watermarking