Attributing Image Generative Models using Latent Fingerprints
This addresses the need for effective attribution in open-source generative models to prevent malicious use, representing an incremental improvement over existing fingerprinting techniques.
The paper tackles the problem of attributing generative models to mitigate misuse risks by proposing a fingerprinting method using latent semantic dimensions, achieving a better tradeoff between attribution accuracy and generation quality with minimal computational requirements compared to previous state-of-the-art methods.
Generative models have enabled the creation of contents that are indistinguishable from those taken from nature. Open-source development of such models raised concerns about the risks of their misuse for malicious purposes. One potential risk mitigation strategy is to attribute generative models via fingerprinting. Current fingerprinting methods exhibit a significant tradeoff between robust attribution accuracy and generation quality while lacking design principles to improve this tradeoff. This paper investigates the use of latent semantic dimensions as fingerprints, from where we can analyze the effects of design variables, including the choice of fingerprinting dimensions, strength, and capacity, on the accuracy-quality tradeoff. Compared with previous SOTA, our method requires minimum computation and is more applicable to large-scale models. We use StyleGAN2 and the latent diffusion model to demonstrate the efficacy of our method.