Say No to Freeloader: Protecting Intellectual Property of Your Deep Model

Code release for "Say No to Freeloader: Protecting Intellectual Property of Your Deep Model" (PAMI 2024)

Paper

Say No to Freeloader: Protecting Intellectual Property of Your Deep Model (PAMI 2024)

We propose a Compact Un-transferable Pyramid Isolation Domain (CUPI-Domain) which serves as a barrier against illegal transfers from authorized to unauthorized domains, to protect the intellectual property (IP) of AI models.

Prerequisites

The code is implemented with CUDA 11.4, Python 3.8.5 and Pytorch 1.8.0.

Datasets

MNIST

MNIST dataset can be found here.

USPS

USPS dataset can be found here.

SVHN

SVHN dataset can be found here.

MNIST-M

MNIST-M dataset can be found here.

CIFAR-10

CIFAR-10 dataset can be found here.

STL-10

CIFAR-10 dataset can be found here.

VisDA 2017

VisDA 2017 dataset can be found here.

Office-Home

Office-Home dataset can be found here.

DomainNet

DomainNet dataset can be found here.

Running the code

Target-Specified CUPI-Domain

python train_ts_dight.py

Ownership Verification by CUPI-Domain

python train_owner_dight.py

Target-free CUPI-Domain

python train_tf_dight.py

Applicability Authorization by CUPI-Domain

python train_author_dight.py

Citation

If you find this code useful for your research, please cite our paper:

@article{wang2024say,
  title={Say No to Freeloader: Protecting Intellectual Property of Your Deep Model},
  author={Wang, Lianyu and Wang, Meng and Fu, Huazhu and Zhang, Daoqaing},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2024},
  publisher={IEEE}
}

Acknowledgements

Some codes are adapted from NTL and SWIN-Transformer. We thank them for their excellent projects.

Contact

If you have any problem about our code, feel free to contact

• lywang12@126.com
• wangmeng9218@126.com

or describe your problem in Issues.