Embedding Inversion via Conditional Masked Diffusion: recover original text from embedding vectors using parallel denoising. Live demo + training pipeline + technical report.
-
Updated
Feb 12, 2026 - Python
Embedding Inversion via Conditional Masked Diffusion: recover original text from embedding vectors using parallel denoising. Live demo + training pipeline + technical report.
This project explores the efficacy of machine unlearning methods like Task-Agnostic Machine Unlearning and SISA in enhancing privacy and reducing bias in facial recognition systems, emphasizing their importance in responsible technology implementation.
Add a description, image, and links to the privacy-attack topic page so that developers can more easily learn about it.
To associate your repository with the privacy-attack topic, visit your repo's landing page and select "manage topics."