Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 36 of its 57 references that are in the map. First posted on arXiv 20 Mar 2023.
Builds on
36 of 57 references.
References · 36
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
24 more
- 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
- 2021Domain Generalization: A Surveycited by 760
- 2020Image Segmentation Using Deep Learning: A Surveycited by 659
- 2018Deep Visual Domain Adaptation: A Surveycited by 634
- 2017VisDA: The Visual Domain Adaptation Challengecited by 432
- 2016A Learned Representation For Artistic Stylecited by 340
- 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
- 2022Transformers in Medical Imaging: A Surveycited by 245
- 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
- 2017Machine Learning Models that Remember Too Muchcited by 165
- 2017Domain Adaptation for Visual Applications: A Comprehensive Surveycited by 127
- 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
- 2018Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Datacited by 94
- 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
- 2021Transferable Semantic Augmentation for Domain Adaptationcited by 56
- 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
- 2021Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorizationcited by 50
- 2019REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Datacited by 40
- 2018Digital Watermarking for Deep Neural Networkscited by 37
- 2020Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluationscited by 30
- 2022Free Fine-tuning: A Plug-and-Play Watermarking Scheme for Deep Neural Networkscited by 14
- 2017Self-ensembling for visual domain adaptationcited by 12
- 2020Deep-Lock: Secure Authorization for Deep Neural Networkscited by 10
- 2021Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotatorcited by 8
Built on by
Citing papers per year: 2024: 5; 2025: 8; 2026: 1.
14 papers.
Sort:
By area:
- 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learningcited by 17
- 2024SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Modelscited by 16
- 2025Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguisingcited by 8
- 2024Say No to Freeloader: Protecting Intellectual Property of Your Deep Modelcited by 7
- 2025Toward Robust Non-Transferable Learning: A Survey and Benchmarkcited by 7
- 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Needcited by 5
- 2024MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protectioncited by 4
- 2025Vision-Language Model IP Protection via Prompt-based Learningcited by 3
- 2024Non-transferable Pruningcited by 2
- 2025FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypescited by 1
- 2025Patronus: Safeguarding Text-to-Image Models against White-Box Adversariescited by 1
- 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detectioncited by 0
- 2026Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs5 Mar 2026
- 2025Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries18 Oct 2025
- 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need5 Jul 2025
- 2025Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising21 Mar 2025
- 2025ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction17 Mar 2025
- 2025Vision-Language Model IP Protection via Prompt-based Learning4 Mar 2025
- 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detection28 Feb 2025
- 2025FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes22 Feb 2025
- 2025Toward Robust Non-Transferable Learning: A Survey and Benchmark19 Feb 2025
- 2024Non-transferable Pruning10 Oct 2024
- 2024Say No to Freeloader: Protecting Intellectual Property of Your Deep Model23 Aug 2024
- 2024SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models19 Apr 2024
- 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learningcited by 17
- 2024SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Modelscited by 16
- 2024Say No to Freeloader: Protecting Intellectual Property of Your Deep Modelcited by 7
- 2025Toward Robust Non-Transferable Learning: A Survey and Benchmarkcited by 7
- 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Needcited by 5
- 2024MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protectioncited by 4
- 2024Non-transferable Pruningcited by 2
- 2025FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypescited by 1
- 2025Patronus: Safeguarding Text-to-Image Models against White-Box Adversariescited by 1
- 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detectioncited by 0
- 2025ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extractioncited by 0
- 2026Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMscited by 0
- 2026Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs5 Mar 2026
- 2025Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries18 Oct 2025
- 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need5 Jul 2025
- 2025ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction17 Mar 2025
- 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detection28 Feb 2025
- 2025FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes22 Feb 2025
- 2025Toward Robust Non-Transferable Learning: A Survey and Benchmark19 Feb 2025
- 2024Non-transferable Pruning10 Oct 2024
- 2024Say No to Freeloader: Protecting Intellectual Property of Your Deep Model23 Aug 2024
- 2024SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models19 Apr 2024
- 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning23 Mar 2024
- 2024MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection7 Mar 2024