Attributing Image Generative Models using Latent Fingerprints. (arXiv:2304.09752v1 [cs.CV])

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 …

attribution current design development fingerprinting fingerprints generative malicious mitigation nature principles quality risk risk mitigation risks strategy taken