What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks
In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis. However, well-trained GANs are under the threat of illegal steal or leakage. The prior studies on remote ownership verification assume a black-box setting where the defender can query the suspicious model with specific inputs, which we identify is not enough for generation tasks. To this end, in this paper, we propose a novel IP protection scheme for GANs where ownership verification can be done by checking outputs only, without choosing the inputs (i.e., box-free setting). Specifically, we make use of the unexploited potential of the discriminator to learn a hypersphere that captures the unique distribution learned by the paired generator. Extensive evaluations on two popular GAN tasks and more than 10 GAN architectures demonstrate our proposed scheme to effectively verify the ownership. Our proposed scheme shown to be immune to popular input-based removal attacks and robust against other existing attacks. The source code and models are available at https://github.com/AbstractTeen/gan_ownership_verification.
Code (1)
Tasks
Generative Adversarial NetworkImage GenerationSimilar Papers 제목 키워드 기반
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network
In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis. However, well-trained GANs are under the threat of illegal steal or leakage. The prior stud…
Generative Adversarial NetworkImage GenerationKnowledge-Free Black-Box Watermark and Ownership Proof for Image Classification Neural Networks
Watermarking has become a plausible candidate for ownership verification and intellectual property protection of deep neural networks. Regarding image classification neural networks, current watermarking schemes uniforml…
image-classificationImage ClassificationOVLA: Neural Network Ownership Verification using Latent Watermarks
Ownership verification for neural networks is important for protecting these models from illegal copying, free-riding, re-distribution and other intellectual property misuse. We present a novel methodology for neural net…
Data PoisoningCertDW: Towards Certified Dataset Ownership Verification via Conformal Prediction
Deep neural networks (DNNs) rely heavily on high-quality open-source datasets (e.g., ImageNet) for their success, making dataset ownership verification (DOV) crucial for protecting public dataset copyrights. In this pape…
Conformal PredictionFedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
Training Latent Diffusion Models (LDMs) within Federated Learning (FL) has attracted increasing attention due to its ability to combine the powerful generative capacity of LDMs with the privacy-preserving properties of F…
Federated Learning