Generative models have enabled the creation of contents that are
indistinguishable from those taken from the nature. Open-source development of
such models raised concerns about the risks in their misuse for malicious
purposes. One potential risk mitigation strategy is to attribute generative
models via fingerprinting. Current fingerprinting methods exhibit significant
tradeoff between robust attribution accuracy and generation quality, and also
lack designing 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.

本文研究了使用潜在语义维度作为指纹的方法，以分析设计变量对准确性和质量之间的权衡的影响。与当前 SOTA 相比，我们的方法需要最少的计算量，并且更适用于大规模模型。我们使用 StyleGAN2 和潜在扩散模型来证明我们的方法的有效性。