Decentralized Attribution of Generative Models
This work addresses scalability and guarantee issues in model attribution for generative models, which is crucial for security and copyright protection in applications like digital media, but it is incremental as it builds on existing centralized approaches.
The paper tackles the problem of attributing generated content to specific user-end models to address threats like malicious impersonation and copyright infringement, proposing a decentralized attribution method that uses user-specific keys to guarantee an attributability lower bound and validating it on datasets such as MNIST, CelebA, and FFHQ with analysis of trade-offs between generation quality and robustness.
Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the contents under question are generated from. Existing studies showed empirical feasibility of attribution through a centralized classifier trained on all user-end models. However, this approach is not scalable in reality as the number of models ever grows. Neither does it provide an attributability guarantee. To this end, this paper studies decentralized attribution, which relies on binary classifiers associated with each user-end model. Each binary classifier is parameterized by a user-specific key and distinguishes its associated model distribution from the authentic data distribution. We develop sufficient conditions of the keys that guarantee an attributability lower bound. Our method is validated on MNIST, CelebA, and FFHQ datasets. We also examine the trade-off between generation quality and robustness of attribution against adversarial post-processes.