Dec. 9, 2023, 3:41 p.m. | Yannic Kilcher

Yannic Kilcher www.youtube.com

This paper outlines how, under certain circumstances, text embeddings can be used to reconstruct the original embedded text.

OUTLINE:
0:00 - Intro
6:50 - Vec2Text: Iterative Embedding Inversion
12:20 - How to train this?
21:20 - Experimental results
26:10 - How can we prevent this?
31:20 - Some thoughts on sequence lengths

Paper: https://arxiv.org/abs/2310.06816

Abstract:
How much private information do text embeddings reveal about the original text? We investigate the problem of embedding \textit{inversion}, reconstructing the full text represented in …

embedded embedding embeddings experimental intro iterative outlines paper text thoughts train

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Consultant Senior Power BI & Azure - CDI - H/F

@ Talan | Lyon, France