diffGHOST is a conditional diffusion model that segments learned latent space to identify and mitigate memorization of critical trajectory samples, aiming to deliver privacy guarantees alongside data utility.
PLoS computational biology10(7), e1003716 (2014) diffGHOST 19
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories
diffGHOST is a conditional diffusion model that segments learned latent space to identify and mitigate memorization of critical trajectory samples, aiming to deliver privacy guarantees alongside data utility.