Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings
DAEI is proposed, a denoising-aware embedding inversion pipeline that combines a residual denoising autoencoder with generative text inversion where the denoiser is trained in an unsupervised manner using Stein's unbiased risk estimate to enable denoising from noisy observations alone.
Yubo Wang, Shujie Cui, James Bailey et al.
· 0 citations