all InfoSec news
Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement. (arXiv:2309.07254v4 [cs.CV] UPDATED)
cs.CR updates on arXiv.org arxiv.org
While diffusion models demonstrate a remarkable capability for generating
high-quality images, their tendency to `replicate' training data raises privacy
concerns. Although recent research suggests that this replication may stem from
the insufficient generalization of training data captions and duplication of
training images, effective mitigation strategies remain elusive. To address
this gap, our paper first introduces a generality score that measures the
caption generality and employ large language model (LLM) to generalize training
captions. Subsequently, we leverage generalized captions and propose …
arxiv data diffusion models fusion high images may privacy privacy concerns quality replication research stem training training data