AICYMar 20, 2023

Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection

arXiv:2303.11078v126 citationsh-index: 80
Originality Incremental advance
AI Analysis

This addresses model IP protection for creators and owners, offering a plug-and-play solution, though it appears incremental as it builds on existing domain adaptation and style feature concepts.

The paper tackles the problem of protecting model intellectual property by preventing unauthorized cross-domain transfers, proposing a Compact Un-Transferable Isolation Domain (CUTI-domain) that blocks illegal transfers by highlighting private style features, with experimental validation on datasets like CIFAR10 and VisDA-2017.

As scientific and technological advancements result from human intellectual labor and computational costs, protecting model intellectual property (IP) has become increasingly important to encourage model creators and owners. Model IP protection involves preventing the use of well-trained models on unauthorized domains. To address this issue, we propose a novel approach called Compact Un-Transferable Isolation Domain (CUTI-domain), which acts as a barrier to block illegal transfers from authorized to unauthorized domains. Specifically, CUTI-domain blocks cross-domain transfers by highlighting the private style features of the authorized domain, leading to recognition failure on unauthorized domains with irrelevant private style features. Moreover, we provide two solutions for using CUTI-domain depending on whether the unauthorized domain is known or not: target-specified CUTI-domain and target-free CUTI-domain. Our comprehensive experimental results on four digit datasets, CIFAR10 & STL10, and VisDA-2017 dataset demonstrate that CUTI-domain can be easily implemented as a plug-and-play module with different backbones, providing an efficient solution for model IP protection.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes